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

    Neuronpedia

    INDEX
    Explanations

    handle and interactive widget state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     kawa
    0.46
     afbeelding
    0.43
     näytt
    0.40
     almac
    0.40
     animasi
    0.40
     animación
    0.40
     muestra
    0.39
     previs
    0.39
     kısa
    0.39
     caché
    0.39
    POSITIVE LOGITS
    go
    0.44
    Σ
    0.41
    Click
    0.38
    Button
    0.37
    KeyDown
    0.37
    ÓN
    0.37
    ButtonClick
    0.37
     pushbutton
    0.37
    SPs
    0.37
    CZ
    0.36
    Act Density 0.166%

    No Known Activations