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

    Neuronpedia

    INDEX
    Explanations

    code, formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .IndexOf
    -0.08
    ploy
    -0.07
    قسم
    -0.07
    switch
    -0.07
     eclips
    -0.07
    企图
    -0.07
    _MINUS
    -0.07
    .slot
    -0.07
    .air
    -0.07
    $info
    -0.07
    POSITIVE LOGITS
    퍄
    0.08
    _COORD
    0.08
    �
    0.07
    繁华
    0.07
    omanip
    0.07
    Authorities
    0.07
    umont
    0.07
    rado
    0.07
    Public
    0.06
     preserved
    0.06
    Act Density 0.030%

    No Known Activations