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

    Neuronpedia

    INDEX
    Explanations

    Code/data snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uptime
    -0.07
     silicone
    -0.07
     суп
    -0.06
    !\
    -0.06
    isle
    -0.06
     abdomen
    -0.06
     chorus
    -0.06
    кої
    -0.06
    onces
    -0.06
     Weiss
    -0.06
    POSITIVE LOGITS
     exec
    0.07
     الملك
    0.07
     JMP
    0.07
     Gutenberg
    0.06
    中
    0.06
    .map
    0.06
    	AL
    0.06
    _foreign
    0.06
    .raw
    0.06
     variable
    0.06
    Act Density 0.009%

    No Known Activations