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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations/Placeholders

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Rub
    -0.07
     の
    -0.06
    дем
    -0.06
     possessions
    -0.06
     treated
    -0.06
    YLON
    -0.06
    pData
    -0.06
    čí
    -0.06
    cq
    -0.06
     Member
    -0.06
    POSITIVE LOGITS
    responseData
    0.07
     Kit
    0.06
    .SOCK
    0.06
    _accepted
    0.06
    >'.
    0.06
     Kemal
    0.06
    SPATH
    0.06
    笑
    0.06
     turret
    0.06
     Locate
    0.06
    Act Density 0.015%

    No Known Activations