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

    Neuronpedia

    INDEX
    Explanations

    variations of "world"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    inp
    -0.08
    iate
    -0.07
     mf
    -0.07
    üph
    -0.06
    Gi
    -0.06
     albums
    -0.06
     possible
    -0.06
     حسب
    -0.06
    ibel
    -0.06
    虑
    -0.06
    POSITIVE LOGITS
     GSL
    0.07
     гар
    0.07
    _INDEX
    0.07
     Smartphone
    0.07
    ?
    0.06
     دستور
    0.06
    _YEAR
    0.06
    ARR
    0.06
    _longitude
    0.06
    [right
    0.06
    Act Density 0.029%

    No Known Activations