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

    Neuronpedia

    INDEX
    Explanations

    space

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    format
    -0.07
    -controlled
    -0.07
     warm
    -0.07
     Sonata
    -0.06
     Published
    -0.06
     career
    -0.06
    帯
    -0.06
    旧
    -0.06
    uned
    -0.06
    CLI
    -0.06
    POSITIVE LOGITS
    ์:
    0.07
    _ub
    0.07
     گرد
    0.06
    	memset
    0.06
    abyte
    0.06
    _DIAG
    0.06
    $field
    0.06
     милли
    0.06
     APPLE
    0.06
    ####
    0.06
    Act Density 0.002%

    No Known Activations