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

    Neuronpedia

    INDEX
    Explanations

    responsibility

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _Part
    -0.06
    _collection
    -0.06
    ych
    -0.06
    idf
    -0.06
    Continuous
    -0.06
    ascii
    -0.06
     compagn
    -0.06
     ASCII
    -0.06
     anon
    -0.06
    -cluster
    -0.06
    POSITIVE LOGITS
    ับผ
    0.07
     sexism
    0.07
    figcaption
    0.06
    委
    0.06
    oce
    0.06
    :*
    0.06
    िय
    0.06
     jLabel
    0.06
     recre
    0.06
     launching
    0.06
    Act Density 0.008%

    No Known Activations