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
     Sexual
    -0.08
    ไร
    -0.07
     Getting
    -0.06
    	GL
    -0.06
     powder
    -0.06
     My
    -0.06
    -frame
    -0.06
     forensic
    -0.06
     Income
    -0.06
    (Enum
    -0.06
    POSITIVE LOGITS
     artık
    0.07
    upt
    0.07
    /************************
    0.06
    MER
    0.06
     purposely
    0.06
     okolí
    0.06
    alborg
    0.06
     solitude
    0.06
     multiplic
    0.06
     amour
    0.06
    Act Density 0.014%

    No Known Activations