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

    Neuronpedia

    INDEX
    Explanations

    Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manoe
    -0.08
     expertly
    -0.08
     maneuver
    -0.08
     کیفیت
    -0.07
                 ↵
    -0.07
     monitored
    -0.07
     विशेषज्ञ
    -0.07
    轉
    -0.07
    -0.07
    .duration
    -0.07
    POSITIVE LOGITS
     Ainsi
    0.10
    .symmetric
    0.10
     symmetrical
    0.09
     symmetric
    0.09
     parity
    0.09
    _encrypt
    0.09
     symmetry
    0.09
    Ainsi
    0.08
     antis
    0.08
     Sym
    0.08
    Act Density 0.079%

    No Known Activations