Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    sentences that describe processes and sequences of events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Sentences that continue or elaborate on a previous point

    np_acts-logits-general · gemini-2.0-flash

    sentence ending punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     المعيارى
    -0.48
     sabar
    -0.43
     Sabina
    -0.41
    GeneratedValue
    -0.40
    passport
    -0.39
    __((
    -0.37
    marle
    -0.36
     akka
    -0.36
    macros
    -0.35
     pula
    -0.35
    POSITIVE LOGITS
    EndContext
    0.61
    RTCF
    0.51
    principalTable
    0.50
    SharedCtor
    0.49
     HttpNotFound
    0.46
    tagHelperRunner
    0.46
     '{@
    0.46
    itinéraire
    0.46
     defaultstate
    0.46
    $_['
    0.45
    Act Density 0.748%

    No Known Activations