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

    Neuronpedia

    INDEX
    Explanations

    phrases that indicate challenges and key characteristics within a context

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

    technical concepts and jargon

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Púb
    -0.43
    oneofs
    -0.43
    ifikationer
    -0.42
    BeNil
    -0.40
     typelib
    -0.40
    SharedCtor
    -0.39
    ientí
    -0.39
     themselves
    -0.38
     acci
    -0.37
    omitempty
    -0.36
    POSITIVE LOGITS
    makeText
    0.50
    évaluateur
    0.48
    antMatchers
    0.45
     kağıdı
    0.42
    MemoryWarning
    0.41
    𓃵
    0.41
    今回の
    0.41
    новништво
    0.40
    ГЛА
    0.40
     această
    0.40
    Act Density 0.061%

    No Known Activations