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

    Neuronpedia

    INDEX
    Explanations

    this

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Targets
    -0.07
    Diff
    -0.07
     FF
    -0.07
     GF
    -0.06
     Ziel
    -0.06
    ุมชน
    -0.06
    ології
    -0.06
    Err
    -0.06
     qDebug
    -0.06
     Ti
    -0.06
    POSITIVE LOGITS
     commencement
    0.07
    jc
    0.07
     materially
    0.07
    šku
    0.07
                     ↵
    0.07
    .partition
    0.06
    yalty
    0.06
    isce
    0.06
    搞
    0.06
    rn
    0.06
    Act Density 0.001%

    No Known Activations