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
     Resort
    -0.08
     Kardashian
    -0.07
    IDs
    -0.07
     suspicious
    -0.07
     dating
    -0.07
     Archive
    -0.07
     tonnes
    -0.07
    35
    -0.06
     Matthews
    -0.06
    SW
    -0.06
    POSITIVE LOGITS
     controle
    0.07
    ální
    0.07
     señ
    0.06
    щее
    0.06
     synerg
    0.06
     perce
    0.06
    жа
    0.06
     doubles
    0.06
    ，不
    0.06
     движ
    0.05
    Act Density 0.030%

    No Known Activations