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

    Neuronpedia

    INDEX
    Explanations

    how to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    റ്റ
    0.69
    ie
    0.67
    ्
    0.65
     sabe
    0.62
     circumstances
    0.61
     schrift
    0.61
     weiter
    0.60
     Spannung
    0.60
     Weiter
    0.60
    ्ड
    0.60
    POSITIVE LOGITS
    ementara
    0.74
    علم
    0.73
    عال
    0.71
    ع
    0.71
    𝐑
    0.71
    bati
    0.71
     prominently
    0.70
    EARCH
    0.69
    unfortunately
    0.68
    denly
    0.68
    Act Density 0.051%

    No Known Activations