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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Buchanan
    -0.07
    517
    -0.07
     Comp
    -0.06
    singleton
    -0.06
    Fo
    -0.06
    (that
    -0.06
    bam
    -0.06
    Comp
    -0.06
     Baz
    -0.06
    722
    -0.06
    POSITIVE LOGITS
    :expr
    0.07
    goal
    0.07
    .Repositories
    0.07
    WX
    0.07
    ength
    0.06
    >::
    0.06
     Reflect
    0.06
    書
    0.06
    =torch
    0.06
    .onclick
    0.06
    Act Density 0.011%

    No Known Activations