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

    Neuronpedia

    INDEX
    Explanations

    conditional phrases and terms indicating deliberation or evaluation

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

    extend to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     MSP
    -0.44
    MSP
    -0.44
     GLC
    -0.43
    NCC
    -0.42
     Creed
    -0.41
     Oran
    -0.41
    Gall
    -0.40
     temple
    -0.40
     IAC
    -0.40
    Medio
    -0.40
    POSITIVE LOGITS
    ConstraintMaker
    0.57
    ValueStyle
    0.56
    CppMethod
    0.54
     initComponents
    0.51
    帖最后由
    0.50
    IntoConstraints
    0.49
     alça
    0.48
    astéroïdes
    0.48
     Réponses
    0.48
     invokingState
    0.47
    Act Density 0.059%

    No Known Activations