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

    Neuronpedia

    INDEX
    Explanations

    URLs with paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    스
    0.38
    الج
    0.33
    GER
    0.33
    트
    0.33
     abilit
    0.32
    م
    0.31
    決め
    0.31
    스트
    0.30
    ปล
    0.30
     enigma
    0.30
    POSITIVE LOGITS
    /?
    0.46
    /,
    0.45
    /*.
    0.42
     可愛
    0.40
    /",
    0.39
    /)
    0.37
    /',
    0.37
     εδώ
    0.37
     这个
    0.36
    /),
    0.35
    Act Density 0.101%

    No Known Activations