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

    Neuronpedia

    INDEX
    Explanations

    drawing or game screen

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    त्रेयी
    0.33
     καὶ
    0.32
    WARD
    0.31
    Lindsay
    0.31
    SERVICIO
    0.30
    UTONIUM
    0.30
     nécessairement
    0.30
    AIRMAN
    0.30
    𝘂
    0.30
    ZIE
    0.30
    POSITIVE LOGITS
     whatnot
    0.32
     Keyboard
    0.31
     पढ
    0.31
     portals
    0.29
     güçlü
    0.29
     Icons
    0.28
     rhythm
    0.27
     fierce
    0.27
     polka
    0.27
     detectar
    0.27
    Act Density 0.070%

    No Known Activations