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

    Neuronpedia

    INDEX
    Explanations

    sexual content

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     table
    -0.08
    cek
    -0.07
     легко
    -0.07
     hoàn
    -0.07
    579
    -0.06
    18
    -0.06
     sax
    -0.06
    :["
    -0.06
    deps
    -0.06
    ITO
    -0.06
    POSITIVE LOGITS
    찌
    0.06
     Gdk
    0.06
    振
    0.06
    vrier
    0.06
    Reached
    0.06
    木
    0.06
    字段
    0.06
     कव
    0.06
    _CRITICAL
    0.06
    byterian
    0.06
    Act Density 0.052%

    No Known Activations