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

    Neuronpedia

    INDEX
    Explanations

    general writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     meet
    -0.63
    ≦)
    -0.59
     play
    -0.59
     make
    -0.59
     kill
    -0.58
     act
    -0.58
     sell
    -0.58
     keep
    -0.58
     take
    -0.57
     stand
    -0.57
    POSITIVE LOGITS
     seeing
    0.79
     dealing
    0.73
     hearing
    0.73
    GEBURTSDATUM
    0.71
    <bos>
    0.68
    IsContent
    0.66
     handing
    0.65
     owning
    0.62
     encountering
    0.60
     relying
    0.60
    Act Density 0.002%

    No Known Activations