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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     obscene
    -0.06
     cultured
    -0.06
     Filip
    -0.06
    ovali
    -0.06
    icks
    -0.06
     KN
    -0.06
     همکاری
    -0.06
     infographic
    -0.06
     Ung
    -0.06
     getArguments
    -0.06
    POSITIVE LOGITS
    	↵	↵
    0.07
    ={
    0.07
    	↵	↵	↵
    0.07
    nutí
    0.07
    CLUDING
    0.06
    uuid
    0.06
    420
    0.06
    [:,:,
    0.06
    권
    0.06
    /debug
    0.06
    Act Density 0.011%

    No Known Activations