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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AMPL
    -0.08
    -feedback
    -0.07
     Growth
    -0.07
     donner
    -0.07
    VarChar
    -0.07
     dictator
    -0.07
     problems
    -0.07
     BO
    -0.07
    Jackson
    -0.07
    .admin
    -0.06
    POSITIVE LOGITS
    ну
    0.06
    ROLS
    0.06
     Builders
    0.06
    _SIZE
    0.06
     FetchType
    0.06
    .LoadScene
    0.06
     Disqus
    0.06
    REATE
    0.06
    rescia
    0.06
     其他
    0.05
    Act Density 0.006%

    No Known Activations