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

    Neuronpedia

    INDEX
    Explanations

    test zero division, different levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ങ്ങളാണ്
    0.73
    oing
    0.70
    ેલા
    0.69
    ар
    0.69
    τα
    0.68
    िरण
    0.66
    eted
    0.64
    ታት
    0.64
     forecast
    0.63
    ारीरिक
    0.61
    POSITIVE LOGITS
     וא
    0.78
     बंधन
    0.77
     ממש
    0.77
    kumar
    0.76
     ת
    0.76
     הם
    0.75
     ג
    0.75
    การ
    0.74
    VerFile
    0.73
    Ν
    0.73
    Act Density 0.765%

    No Known Activations