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

    Neuronpedia

    INDEX
    Explanations

    resolves issues

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ны
    0.46
     Assist
    0.38
     CallOptions
    0.38
    rivel
    0.37
     некоторы
    0.37
    大战
    0.36
     Tiber
    0.35
     Zeitschrift
    0.35
    INED
    0.35
     Assistance
    0.34
    POSITIVE LOGITS
     solves
    1.48
     해결
    1.41
     solve
    1.34
    解决
    1.34
    解決
    1.33
    解决了
    1.28
     solving
    1.25
     solved
    1.19
     cure
    1.18
     cures
    1.16
    Act Density 0.016%

    No Known Activations