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

    Neuronpedia

    INDEX
    Explanations

    surfing lessons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     द्रव
    0.56
     speciale
    0.55
     особы
    0.55
     superbly
    0.54
     to
    0.51
     sanitize
    0.51
     preside
    0.50
     mandar
    0.50
     وزیراعظم
    0.49
    صله
    0.49
    POSITIVE LOGITS
    odesmium
    0.53
    ಸ
    0.47
    mo
    0.47
    pul
    0.46
    po
    0.42
    pa
    0.41
    ínio
    0.41
    I
    0.41
    oss
    0.40
    æk
    0.40
    Act Density 0.000%

    No Known Activations