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

    Neuronpedia

    INDEX
    Explanations

    St. West

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     shameful
    0.45
     killings
    0.45
     død
    0.44
     molest
    0.43
     ancestors
    0.42
     знако
    0.42
     मौत
    0.41
    ходе
    0.41
    ስታ
    0.41
    メッセージ
    0.41
    POSITIVE LOGITS
     Nutritional
    0.46
     Optional
    0.41
     portion
    0.40
     Positioning
    0.40
    ipe
    0.39
     Delegate
    0.37
     AMC
    0.36
    Optional
    0.36
    antam
    0.36
     Webinar
    0.36
    Act Density 0.002%

    No Known Activations