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

    Neuronpedia

    INDEX
    Explanations

    reference

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _kwargs
    -0.07
    常州
    -0.07
     autoFocus
    -0.07
     שנה
    -0.07
     KB
    -0.06
    _access
    -0.06
    年后
    -0.06
    ذ
    -0.06
     userModel
    -0.06
    쾌
    -0.06
    POSITIVE LOGITS
    ILA
    0.07
     FOREIGN
    0.07
     İnt
    0.07
    _TRIANGLES
    0.07
     Rug
    0.07
    .qty
    0.07
     Snake
    0.07
     airspace
    0.07
    >('
    0.07
    遐
    0.07
    Act Density 0.018%

    No Known Activations