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

    Neuronpedia

    INDEX
    Explanations

    subjective

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AAF
    -0.07
    �
    -0.07
    有关
    -0.07
     gelişim
    -0.07
     ions
    -0.06
     fortn
    -0.06
     чт
    -0.06
    _download
    -0.06
    며
    -0.06
     jeopardy
    -0.06
    POSITIVE LOGITS
     subjective
    0.09
    tracks
    0.06
     OUTER
    0.06
    actic
    0.06
     psyche
    0.06
    cookie
    0.06
     helmet
    0.06
     문
    0.06
    όγ
    0.06
    ivi
    0.06
    Act Density 0.003%

    No Known Activations