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

    Neuronpedia

    INDEX
    Explanations

    references to configuration setup or initialization

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

    initial / initializers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    //
    -0.51
     مرئيه
    -0.48
     ArrayAdapter
    -0.47
    Pyx
    -0.47
    enumi
    -0.44
    lectricité
    -0.44
    ulemon
    -0.41
    DIPSETTING
    -0.40
    ="@+
    -0.39
    kuuta
    -0.39
    POSITIVE LOGITS
    initial
    1.29
     initial
    1.11
     Initial
    1.10
    Initial
    1.05
     INITIAL
    1.02
    INITIAL
    1.00
     initiale
    0.86
    初始
    0.80
     inicial
    0.77
     initially
    0.74
    Act Density 0.000%

    No Known Activations