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

    Neuronpedia

    INDEX
    Explanations

    vividness/variety

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    terminate
    -0.26
    ches
    -0.25
    ëĵ¬
    -0.24
     Closet
    -0.24
    Down
    -0.24
    imon
    -0.23
    onsense
    -0.23
    Lik
    -0.23
    imiters
    -0.23
    дон
    -0.23
    POSITIVE LOGITS
    UGH
    0.28
    ór
    0.26
    åħ´èĩ´
    0.24
    ,,,,
    0.24
    resa
    0.24
     heels
    0.23
    quel
    0.23
    ï¸
    0.23
    гоÑĢ
    0.22
    ðŁĴ¦
    0.22
    Act Density 0.108%

    No Known Activations