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

    Neuronpedia

    INDEX
    Explanations

    word processing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     outcry
    -0.07
    ﻉ
    -0.07
     producers
    -0.07
     Respir
    -0.07
    _chance
    -0.07
    _CLUSTER
    -0.07
    _TS
    -0.06
    gly
    -0.06
     PANEL
    -0.06
     competing
    -0.06
    POSITIVE LOGITS
    Alamat
    0.07
    𦙶
    0.07
    吃过
    0.07
    认同
    0.07
    ita
    0.07
     original
    0.07
    𝐽
    0.06
    等到
    0.06
    反思
    0.06
    릿
    0.06
    Act Density 0.035%

    No Known Activations