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

    Neuronpedia

    INDEX
    Explanations

    programming keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Bucket
    0.70
     collabor
    0.67
     bucket
    0.67
     Bucket
    0.67
     Polarization
    0.66
    Occupation
    0.64
    Louis
    0.64
     Specialty
    0.64
     indium
    0.63
     summits
    0.63
    POSITIVE LOGITS
     goto
    1.10
    else
    1.09
     else
    1.04
    goto
    1.01
     foreach
    1.00
    foreach
    0.93
     switch
    0.93
    break
    0.92
    for
    0.92
     pernyataan
    0.91
    Act Density 0.255%

    No Known Activations