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

    Neuronpedia

    INDEX
    Explanations

    and , or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Aug
    -0.06
     Tanz
    -0.06
    Sorting
    -0.06
     cleric
    -0.06
     Northwestern
    -0.06
    extr
    -0.06
     Yao
    -0.06
    errated
    -0.06
    arrant
    -0.06
     Portland
    -0.05
    POSITIVE LOGITS
    Forms
    0.07
    (deck
    0.07
    -center
    0.06
    =pk
    0.06
     همه
    0.06
    .Image
    0.06
    _SOUND
    0.06
    liced
    0.06
    .IsChecked
    0.06
    言って
    0.06
    Act Density 0.069%

    No Known Activations