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

    Neuronpedia

    INDEX
    Explanations

    Chinese locations

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    JR
    0.40
     JR
    0.39
    ษ
    0.39
     Dove
    0.35
    >…</
    0.35
     Len
    0.35
    zin
    0.34
    염
    0.33
     Brook
    0.33
     prist
    0.33
    POSITIVE LOGITS
    二
    0.61
     二
    0.49
    San
    0.47
    二是
    0.47
     Erg
    0.45
    La
    0.44
     Dab
    0.41
    ULE
    0.41
    erg
    0.40
     Aula
    0.40
    Act Density 0.000%

    No Known Activations