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

    Neuronpedia

    INDEX
    Explanations

    technical discussion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ملك
    0.39
    बाइक
    0.38
    voja
    0.36
     Baked
    0.36
    ynn
    0.36
     రెండు
    0.36
    ूठी
    0.36
    ඖ
    0.35
    klı
    0.35
    奔
    0.35
    POSITIVE LOGITS
     might
    0.47
    かも
    0.47
    might
    0.39
     somehow
    0.38
    かもし
    0.38
    cis
    0.38
     echelon
    0.37
     may
    0.36
     could
    0.36
     link
    0.36
    Act Density 0.000%

    No Known Activations