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

    Neuronpedia

    INDEX
    Explanations

    assessments

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    蹩
    -0.07
    مان
    -0.07
    悻
    -0.07
    赛区
    -0.07
     nb
    -0.07
     aust
    -0.07
     Пред
    -0.07
     Printf
    -0.07
     Hector
    -0.07
     photoc
    -0.07
    POSITIVE LOGITS
     update
    0.07
    \Service
    0.07
     correlations
    0.07
     converted
    0.07
     deployment
    0.07
    bling
    0.07
     adjustments
    0.06
    _fa
    0.06
    ="
    0.06
    ategorical
    0.06
    Act Density 0.113%

    No Known Activations