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

    Neuronpedia

    INDEX
    Explanations

    optional binding

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    0.64
     omfatt
    0.57
    కా
    0.57
    ल
    0.55
    플
    0.52
     skates
    0.52
    ل
    0.52
     pedal
    0.51
     slips
    0.51
     फ्लाईओवर
    0.51
    POSITIVE LOGITS
    GER
    0.63
     će
    0.61
    _%
    0.59
    interno
    0.59
    <{
    0.59
    ਤਰ
    0.59
    OSED
    0.58
    offic
    0.58
    UIManager
    0.58
    LOTRE
    0.58
    Act Density 0.001%

    No Known Activations