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

    Neuronpedia

    INDEX
    Explanations

    structured data formats or identifiers related to content management

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

    user instructions or special commands

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.64
     ſche
    -0.60
     Numerade
    -0.59
    findpost
    -0.58
     ſol
    -0.57
     Chwiliwch
    -0.57
    Javadoc
    -0.55
    ngdoc
    -0.55
    casila
    -0.55
     queſta
    -0.55
    POSITIVE LOGITS
    MetaObject
    0.38
     Ang
    0.38
     Pru
    0.35
    Ang
    0.34
    @
    0.34
     narrowly
    0.32
     deceler
    0.31
     Schott
    0.31
     Schne
    0.31
     Falk
    0.31
    Act Density 0.002%

    No Known Activations