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

    Neuronpedia

    INDEX
    Explanations

    explain action

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     empowered
    0.42
    첸
    0.40
    Recurring
    0.40
    靓
    0.40
    nr
    0.40
    oyeva
    0.39
     elektronik
    0.39
     அம்
    0.39
    ariyam
    0.38
     artı
    0.38
    POSITIVE LOGITS
     goede
    0.51
     gute
    0.50
     Universidade
    0.47
    ను
    0.46
    ល្អ
    0.46
    :
    0.46
     dois
    0.46
    .
    0.45
     sogenannte
    0.45
     fetal
    0.45
    Act Density 0.001%

    No Known Activations