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

    Neuronpedia

    INDEX
    Explanations

    first

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     cultivated
    -0.07
     snake
    -0.07
     Phrase
    -0.06
    ses
    -0.06
    arr
    -0.06
     кораб
    -0.06
    loy
    -0.06
    GetCurrent
    -0.06
    .called
    -0.06
     Showcase
    -0.06
    POSITIVE LOGITS
    _FRONT
    0.07
    .actor
    0.07
    246
    0.07
      
    0.06
     trí
    0.06
    _MAJOR
    0.06
    REV
    0.06
    .AUTH
    0.06
    .vote
    0.06
    .."
    0.06
    Act Density 0.001%

    No Known Activations