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

    Neuronpedia

    INDEX
    Explanations

    ("

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    116
    -0.07
    icí
    -0.07
    !(
    -0.06
    .arc
    -0.06
    NT
    -0.06
    	Y
    -0.06
     dài
    -0.06
     modify
    -0.06
    /***/
    -0.06
    (year
    -0.06
    POSITIVE LOGITS
    dc
    0.07
    .problem
    0.07
    retry
    0.07
    .errors
    0.07
    olkien
    0.06
    .Cells
    0.06
    (figsize
    0.06
    anky
    0.06
     Proposed
    0.06
     Secrets
    0.06
    Act Density 0.037%

    No Known Activations