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

    Neuronpedia

    INDEX
    Explanations

    informal expressions indicating personal thoughts or feelings

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

    but, might, want, occurred, reference

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    UrlResolution
    -0.78
    󠁴
    -0.57
    Tikang
    -0.54
     оригіналу
    -0.54
    Sucesor
    -0.54
     Infórmanos
    -0.53
    GEBURTSDATUM
    -0.50
    falle
    -0.49
     للاسماء
    -0.49
    Essentially
    -0.49
    POSITIVE LOGITS
    Билгалдахарш
    0.32
    offsetof
    0.28
     ważne
    0.27
     remind
    0.27
     vuitton
    0.26
    GIVEREF
    0.26
    noStroke
    0.26
     penting
    0.26
    COLN
    0.26
    /*
    0.25
    Act Density 0.045%

    No Known Activations