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

    Neuronpedia

    INDEX
    Explanations

    liquid silver

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kenneth
    0.40
    <0xC2>
    0.37
     Robert
    0.35
    som
    0.35
    нах
    0.34
    wau
    0.34
    wikipedia
    0.34
     Kell
    0.33
     Hills
    0.33
    Robert
    0.33
    POSITIVE LOGITS
    führen
    0.41
     stets
    0.40
     pygame
    0.38
     acquies
    0.38
    ργ
    0.37
     samband
    0.37
     сцена
    0.37
     proguard
    0.37
     suporte
    0.37
     поддержка
    0.37
    Act Density 0.002%

    No Known Activations