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

    Neuronpedia

    INDEX
    Explanations

    mathematical expressions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -､
    -0.07
    _duplicates
    -0.07
    aliases
    -0.07
    WEBPACK
    -0.06
     Sacr
    -0.06
    -upper
    -0.06
     �
    -0.06
    EXTERN
    -0.06
     سعر
    -0.06
     fantast
    -0.06
    POSITIVE LOGITS
     addressing
    0.08
     addressed
    0.07
    431
    0.07
     girls
    0.06
     address
    0.06
     TIMES
    0.06
    Ich
    0.06
     Ich
    0.06
     JOHN
    0.06
     acceler
    0.06
    Act Density 0.026%

    No Known Activations