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

    Neuronpedia

    INDEX
    Explanations

    repository, devices, methods

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    側
    0.48
     មាន
    0.46
    βο
    0.46
     পাশের
    0.43
     மேற்பர
    0.43
     पेंसिल
    0.43
     remarkably
    0.43
     জনসাধারণের
    0.42
     Twelfth
    0.41
    Twins
    0.41
    POSITIVE LOGITS
    ات
    0.54
     soh
    0.49
     pacote
    0.48
    كان
    0.47
    參数
    0.46
     initialized
    0.44
    tur
    0.42
     tendência
    0.42
    нали
    0.41
    tır
    0.41
    Act Density 0.000%

    No Known Activations