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

    Neuronpedia

    INDEX
    Explanations

    onal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     девушк
    -0.07
     Player
    -0.07
    稑
    -0.07
    (suffix
    -0.07
    瘃
    -0.07
    _counter
    -0.07
     Participant
    -0.06
    女主角
    -0.06
     mysterious
    -0.06
     Established
    -0.06
    POSITIVE LOGITS
    grab
    0.07
     eg
    0.07
    .slug
    0.07
    _deleted
    0.06
    HF
    0.06
     scan
    0.06
     robotic
    0.06
     avons
    0.06
    _portal
    0.06
     esk
    0.06
    Act Density 0.001%

    No Known Activations