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

    Neuronpedia

    INDEX
    Explanations

    words with numbers next to them

    oai_token-act-pair · gemini-2.0-flash

    Mentions years

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     CURIAM
    -0.50
     annual
    -0.49
     createSlice
    -0.49
     autorytatywna
    -0.47
     Ver
    -0.47
     onAnimation
    -0.47
    rami
    -0.46
    :✨
    -0.44
    zic
    -0.44
    ={
    -0.43
    POSITIVE LOGITS
     vuonna
    0.84
     בשנת
    0.77
     през
    0.76
    
    0.63
     عام
    0.63
     disambiguazione
    0.59
     FY
    0.58
     ۲۰۱
    0.57
     Lightboxes
    0.56
     useCallback
    0.56
    Act Density 0.847%

    No Known Activations