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

    Neuronpedia

    INDEX
    Explanations

    phrases related to disclaimers or conditions related to software distribution

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

    as is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     varones
    -0.54
     rajut
    -0.52
    ographers
    -0.50
     kajian
    -0.49
     ibunya
    -0.48
     vertellen
    -0.48
     lecciones
    -0.48
     kağı
    -0.47
     assinatura
    -0.47
    enumi
    -0.46
    POSITIVE LOGITS
    FIS
    0.59
     ſtate
    0.53
     autorytatywna
    0.53
     FIS
    0.51
    AS
    0.51
     neceſſ
    0.48
     TOS
    0.47
    ſelves
    0.47
     ſta
    0.47
     nakalista
    0.46
    Act Density 0.001%

    No Known Activations