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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .J
    -0.07
     cudd
    -0.06
     jihad
    -0.06
     Similar
    -0.06
     sunk
    -0.06
    	handler
    -0.06
     UTIL
    -0.06
    Telegram
    -0.06
     Brigade
    -0.06
     bestowed
    -0.06
    POSITIVE LOGITS
    永久
    0.07
     उसक
    0.07
    (Field
    0.07
    CellValue
    0.06
    Solar
    0.06
    .dirname
    0.06
    ',{'
    0.06
    <Character
    0.06
    あの
    0.06
    (ec
    0.06
    Act Density 0.000%

    No Known Activations