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

    Neuronpedia

    INDEX
    Explanations

    FROM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    女人
    -0.06
    ddit
    -0.06
     gens
    -0.06
     设
    -0.06
    .Se
    -0.06
    alist
    -0.06
     sparked
    -0.06
    .radius
    -0.06
     vielleicht
    -0.06
     jeans
    -0.06
    POSITIVE LOGITS
    تب
    0.06
     funeral
    0.06
    .AppCompatActivity
    0.06
    Everybody
    0.06
    ấ
    0.06
     Elem
    0.06
    vern
    0.06
     presumption
    0.06
    multiply
    0.06
     Hick
    0.06
    Act Density 0.001%

    No Known Activations