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

    Neuronpedia

    INDEX
    Explanations

    marker

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Years
    -0.07
    소를
    -0.06
    院
    -0.06
     sluts
    -0.06
    .answer
    -0.06
     thuộc
    -0.06
    _photos
    -0.06
     Utils
    -0.06
    рукт
    -0.06
    Levels
    -0.06
    POSITIVE LOGITS
     Cellular
    0.07
     což
    0.07
    kB
    0.07
     Tak
    0.06
     와
    0.06
    دیگر
    0.06
     apartheid
    0.06
     ↘
    0.06
    ingerprint
    0.06
    ORIZED
    0.06
    Act Density 0.010%

    No Known Activations