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

    Neuronpedia

    INDEX
    Explanations

    many languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Rainy
    0.31
     গাঙ্গুল
    0.30
     Mighty
    0.29
     Lakh
    0.29
     һәм
    0.28
     Mountain
    0.28
     Piper
    0.28
     Percol
    0.28
     Mir
    0.27
     powdered
    0.27
    POSITIVE LOGITS
    efois
    0.38
    fois
    0.38
     vezes
    0.33
     yandan
    0.32
    तः
    0.31
    že
    0.31
     fois
    0.31
    quiera
    0.31
    seits
    0.30
    жды
    0.29
    Act Density 0.049%

    No Known Activations