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

    Neuronpedia

    INDEX
    Explanations

    lost his voice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    p
    0.59
    in
    0.56
     in
    0.54
    There
    0.52
    tiktok
    0.52
    n
    0.52
    Hor
    0.52
    public
    0.51
    I
    0.51
    Urban
    0.50
    POSITIVE LOGITS
    쥬
    0.54
    itipi
    0.52
    getImageFolder
    0.52
     Василий
    0.51
     hati
    0.50
     río
    0.50
     suyu
    0.50
     clockRadius
    0.50
    ҉
    0.50
     Сред
    0.49
    Act Density 0.000%

    No Known Activations