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

    Neuronpedia

    INDEX
    Explanations

    code environments and multilingual text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    O
    0.56
    A
    0.42
     plazas
    0.42
    ppe
    0.41
    OL
    0.41
    Ah
    0.41
    Dal
    0.41
    e
    0.40
     applications
    0.40
    Access
    0.40
    POSITIVE LOGITS
     तुमच्या
    0.47
     معك
    0.43
     држа
    0.43
     ভগব
    0.43
     ὑ
    0.43
     совет
    0.42
    还会
    0.42
     conseil
    0.41
     wichtige
    0.41
     लिंक
    0.41
    Act Density 0.000%

    No Known Activations