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

    Neuronpedia

    INDEX
    Explanations

    related to video or photo

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     either
    -0.98
     Either
    -0.84
    appartement
    -0.82
    ပ
    -0.80
     gagné
    -0.79
     contribué
    -0.78
    あっという
    -0.77
    tatuaje
    -0.77
    Lü
    -0.77
     высокая
    -0.76
    POSITIVE LOGITS
     as
    1.00
     below
    0.98
     nedan
    0.85
     dibawah
    0.84
     HERE
    0.83
    ;
    0.83
    اصله
    0.81
     how
    0.81
     Lotus
    0.80
     etter
    0.79
    Act Density 0.010%

    No Known Activations