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
    CACHE
    -0.07
    spam
    -0.07
     roc
    -0.07
     Shooting
    -0.07
    �
    -0.06
    Ve
    -0.06
     Birds
    -0.06
     Henry
    -0.06
    _PS
    -0.06
     bland
    -0.06
    POSITIVE LOGITS
     trig
    0.06
    >{
    0.06
    _exchange
    0.06
    /TT
    0.06
     메
    0.06
     numero
    0.05
     psyched
    0.05
     изготов
    0.05
     سرمایه
    0.05
     Sask
    0.05
    Act Density 0.033%

    No Known Activations