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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IDS
    -0.07
    .AutoField
    -0.07
     SPORT
    -0.07
     poly
    -0.06
     shifts
    -0.06
    ffset
    -0.06
    _fk
    -0.06
     opi
    -0.06
     TODAY
    -0.06
     identified
    -0.06
    POSITIVE LOGITS
     деньги
    0.07
    ครงการ
    0.07
     yolu
    0.06
     dlg
    0.06
    Information
    0.06
    (project
    0.06
     vandalism
    0.06
    ophone
    0.06
    Rick
    0.06
     fatto
    0.06
    Act Density 0.054%

    No Known Activations