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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tamamen
    -0.06
     Analyzer
    -0.06
     District
    -0.06
    кор
    -0.06
     석
    -0.06
     ниже
    -0.06
    _rho
    -0.06
    (ver
    -0.06
     Ну
    -0.06
     suites
    -0.06
    POSITIVE LOGITS
    -ft
    0.07
    jectives
    0.07
     fontStyle
    0.07
    vio
    0.07
    MemoryWarning
    0.06
     spont
    0.06
    coration
    0.06
     stal
    0.06
     finalists
    0.06
     dumping
    0.06
    Act Density 0.101%

    No Known Activations