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
    .classes
    -0.06
    ercial
    -0.06
    since
    -0.06
    -align
    -0.06
    ‌گ
    -0.06
     신규
    -0.06
    OURCE
    -0.06
     WF
    -0.06
    hyper
    -0.06
    nist
    -0.06
    POSITIVE LOGITS
     phil
    0.07
    �
    0.06
     Initializes
    0.06
     Jets
    0.06
    、私
    0.06
    /id
    0.06
    řit
    0.06
    ,label
    0.06
    �
    0.06
     emot
    0.06
    Act Density 0.019%

    No Known Activations