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

    Neuronpedia

    INDEX
    Explanations

    ideally

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    pees
    -0.08
    _comp
    -0.08
    ópez
    -0.07
    Eine
    -0.07
    جيل
    -0.07
    comp
    -0.07
    лов
    -0.07
    .rabbit
    -0.07
    咛
    -0.07
    从严
    -0.07
    POSITIVE LOGITS
     gunmen
    0.08
    옼
    0.08
     setattr
    0.07
    iders
    0.07
    𝐋
    0.07
    FK
    0.07
     FORM
    0.07
    [channel
    0.07
    んじゃないか
    0.07
    .indices
    0.07
    Act Density 0.006%

    No Known Activations