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

    Neuronpedia

    INDEX
    Explanations

    desire to perform action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ️
    0.99
    ન્ન
    0.96
     необходимо
    0.95
    менение
    0.94
    га
    0.92
    发出
    0.92
    稈
    0.91
     adequado
    0.91
     tö
    0.90
     densité
    0.89
    POSITIVE LOGITS
     know
    1.26
    ﻪ
    0.92
    know
    0.88
     hear
    0.85
     Know
    0.80
     see
    0.78
     Territorial
    0.77
     learn
    0.77
    ंना
    0.77
     happen
    0.76
    Act Density 0.583%

    No Known Activations