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

    Neuronpedia

    INDEX
    Explanations

    simply

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     profitable
    -0.07
    Severity
    -0.07
    (packet
    -0.07
    xFE
    -0.06
    '].'
    -0.06
     coefficients
    -0.06
    jà
    -0.06
    Entre
    -0.06
    delta
    -0.06
    ۲۸
    -0.06
    POSITIVE LOGITS
     simply
    0.10
     Simpson
    0.09
     Simply
    0.08
     
    0.08
    ini
    0.07
     порядке
    0.07
     Bankası
    0.07
     林
    0.07
    utherford
    0.07
    INI
    0.07
    Act Density 0.011%

    No Known Activations