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

    Neuronpedia

    INDEX
    Explanations

    what is

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nouvelles
    0.48
    त
    0.47
    ériences
    0.47
    場合
    0.46
    ં
    0.46
    აზ
    0.46
    Го
    0.46
     constructively
    0.46
    वे
    0.45
     बिंदु
    0.44
    POSITIVE LOGITS
     liczba
    0.52
    ]`
    0.45
    ]^
    0.44
     اخ
    0.44
     karena
    0.44
     لانه
    0.43
     زیرا
    0.43
     可以
    0.43
    wipe
    0.43
    YW
    0.43
    Act Density 0.006%

    No Known Activations