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

    Neuronpedia

    INDEX
    Explanations

    lay out

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     in
    0.58
    ag
    0.52
    ine
    0.51
    K
    0.50
    all
    0.49
    在
    0.48
    ↵
    0.47
    any
    0.47
    et
    0.47
    and
    0.46
    POSITIVE LOGITS
    FocusValue
    0.55
    überkü
    0.52
     божомолдор
    0.52
     وړاندوینې
    0.49
    இல்
    0.49
     रोमांच
    0.48
     квар
    0.47
    ലെസ്
    0.47
    এরপর
    0.47
    ियोग्राफी
    0.46
    Act Density 0.005%

    No Known Activations