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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     воду
    -0.08
    ここ
    -0.07
     khác
    -0.07
     JSBracketAccess
    -0.07
    .MODE
    -0.06
     MULT
    -0.06
     پشت
    -0.06
     культур
    -0.06
     věcí
    -0.06
    結婚
    -0.06
    POSITIVE LOGITS
    ensibly
    0.07
    iber
    0.07
     Serbian
    0.07
    suit
    0.07
    astype
    0.06
     type
    0.06
     Avenue
    0.06
    _warnings
    0.06
    Slide
    0.06
     beating
    0.06
    Act Density 0.012%

    No Known Activations