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

    Neuronpedia

    INDEX
    Explanations

    themes related to understanding concepts and experiences

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

    now, understood

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    -0.66
    UserScript
    -0.59
    $_['
    -0.57
    IntoConstraints
    -0.57
    oredCriteria
    -0.50
     FetchType
    -0.50
    __);
    -0.49
     GenerationType
    -0.48
    AndEndTag
    -0.48
    DispatchToProps
    -0.48
    POSITIVE LOGITS
     now
    0.67
     теперь
    0.63
     ahora
    0.59
     sekarang
    0.57
     ngayon
    0.56
     désormais
    0.53
     obecnie
    0.53
    now
    0.53
     kini
    0.52
     dabar
    0.51
    Act Density 0.070%

    No Known Activations