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
     undefined
    -0.06
     vomiting
    -0.05
     convers
    -0.05
     experimentation
    -0.05
    Wir
    -0.05
    și
    -0.05
     gắng
    -0.05
     professionalism
    -0.05
    _probability
    -0.05
     Nim
    -0.05
    POSITIVE LOGITS
     треб
    0.07
    (values
    0.07
    دا
    0.06
    !$
    0.06
    井
    0.06
    94
    0.06
    ,j
    0.06
    IMATION
    0.06
    /window
    0.06
    (propertyName
    0.06
    Act Density 0.004%

    No Known Activations