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

    Neuronpedia

    INDEX
    Explanations

    start of a numbered list item

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     most
    0.35
    away
    0.34
     ideal
    0.33
     retracted
    0.33
    */}
    0.33
    most
    0.32
    理想
    0.31
     fingers
    0.31
    agan
    0.31
    hor
    0.31
    POSITIVE LOGITS
     Schritt
    0.46
     étape
    0.44
     étapes
    0.43
     เลือก
    0.43
     Bước
    0.42
     passo
    0.40
     bước
    0.40
     ofx
    0.40
     단계
    0.40
     réseau
    0.39
    Act Density 0.022%

    No Known Activations