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

    Neuronpedia

    INDEX
    Explanations

    universal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     snake
    -0.06
     apopt
    -0.06
    $d
    -0.06
    _ob
    -0.06
    :(
    -0.06
    Encryption
    -0.06
     snakes
    -0.06
    +')
    -0.06
     rhythms
    -0.06
     passport
    -0.06
    POSITIVE LOGITS
    /')
    0.07
    /small
    0.06
    ."<
    0.06
    ificacion
    0.06
    永久
    0.06
    ाय
    0.06
    shouldReceive
    0.06
    -interest
    0.06
    _SUITE
    0.06
    phans
    0.06
    Act Density 0.117%

    No Known Activations