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

    Neuronpedia

    INDEX
    Explanations

    non-english phrases and code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    A
    0.64
    v
    0.58
    The
    0.57
    w
    0.57
    *
    0.55
    ‎
    0.55
     U
    0.54
    P
    0.54
    U
    0.54
     auf
    0.54
    POSITIVE LOGITS
     پیغمبر
    0.63
     takePhotoButton
    0.62
     çöze
    0.59
     हमरे
    0.58
     necesitamos
    0.58
    apayati
    0.57
     precisamos
    0.57
     devemos
    0.57
     нәрсә
    0.56
    avasena
    0.55
    Act Density 0.036%

    No Known Activations