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

    Neuronpedia

    INDEX
    Explanations

    state and state management functions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ep
    0.46
    ي
    0.46
    ا
    0.45
    يي
    0.44
    سيط
    0.42
    اح
    0.40
    chtig
    0.39
    ى
    0.39
    ്ര
    0.38
    ونية
    0.38
    POSITIVE LOGITS
    hood
    0.67
    gies
    0.66
     createState
    0.62
     state
    0.56
     getState
    0.56
     State
    0.55
    newState
    0.54
     राज्य
    0.53
     newState
    0.52
     setState
    0.52
    Act Density 0.022%

    No Known Activations