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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nose
    -0.08
    .Model
    -0.07
     Ecuador
    -0.07
     продолж
    -0.07
    女
    -0.06
     movie
    -0.06
     Model
    -0.06
     binary
    -0.06
     Rugby
    -0.06
     Asset
    -0.06
    POSITIVE LOGITS
     při
    0.07
    religious
    0.06
     spre
    0.06
    moduleName
    0.06
     SVN
    0.06
     öğ
    0.06
     vg
    0.06
    tring
    0.06
    LinearLayout
    0.06
     قاب
    0.06
    Act Density 0.015%

    No Known Activations