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

    Neuronpedia

    INDEX
    Explanations

    concepts related to purity and clarity in various contexts

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

    pure essence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    esModule
    -0.60
    OOTDTY
    -0.56
    sizeCache
    -0.55
    ScopeManager
    -0.54
    DNEY
    -0.53
     protoimpl
    -0.49
    TypedDataSet
    -0.48
    aarrggbb
    -0.47
    पया
    -0.46
    kenstock
    -0.44
    POSITIVE LOGITS
     exemplify
    0.36
    oty
    0.35
    SIN
    0.35
    0.34
    SuppressLint
    0.33
     מוש
    0.33
    roth
    0.33
     Bliss
    0.33
     invokingState
    0.32
     sin
    0.32
    Act Density 0.110%

    No Known Activations