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

    Neuronpedia

    INDEX
    Explanations

    otherwise

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .mob
    -0.08
    許
    -0.07
     結
    -0.06
     ее
    -0.06
     glaciers
    -0.06
     validators
    -0.06
    .fetchall
    -0.06
     bathtub
    -0.06
    .DropDownItems
    -0.06
     cof
    -0.06
    POSITIVE LOGITS
    yt
    0.07
    _SEC
    0.07
    \Config
    0.07
    856
    0.07
    умент
    0.07
    _define
    0.07
    _puts
    0.07
    ०
    0.06
    uled
    0.06
     рівень
    0.06
    Act Density 0.001%

    No Known Activations