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

    Neuronpedia

    INDEX
    Explanations

    unusual characters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Vibr
    -0.06
    uzzer
    -0.06
     '='
    -0.06
     sacks
    -0.06
    امین
    -0.06
    uforia
    -0.06
     plagiarism
    -0.06
     SHE
    -0.06
    oodles
    -0.06
    _splits
    -0.05
    POSITIVE LOGITS
     ess
    0.08
     Nov
    0.07
     newState
    0.07
     �
    0.07
    宣
    0.07
     lineage
    0.06
    益
    0.06
    -settings
    0.06
     DVD
    0.06
    Во
    0.06
    Act Density 0.000%

    No Known Activations