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

    Neuronpedia

    INDEX
    Explanations

    articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ..
    -0.08
    ude
    -0.08
    ightly
    -0.07
    ollen
    -0.07
    ACE
    -0.07
    %!
    -0.07
    +%
    -0.07
    (),"
    -0.07
    olumn
    -0.07
    	glEnable
    -0.07
    POSITIVE LOGITS
    Resolver
    0.07
     друз
    0.07
     análisis
    0.07
     Lara
    0.07
     duplicates
    0.07
    exas
    0.07
    _rnn
    0.06
    .reset
    0.06
    _eta
    0.06
    乾
    0.06
    Act Density 0.125%

    No Known Activations