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

    Neuronpedia

    INDEX
    Explanations

    fate and its consequences

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ان
    0.67
    ्
    0.67
    eing
    0.65
    ्ह
    0.62
    т
    0.61
    _=
    0.60
    Says
    0.59
    ej
    0.59
    ியில்
    0.58
    surname
    0.58
    POSITIVE LOGITS
     odpově
    0.81
     produktów
    0.76
     écriv
    0.75
     critères
    0.75
     tendre
    0.74
    ｅ
    0.74
     itemBuilder
    0.74
     petits
    0.74
     dilig
    0.73
     daraus
    0.73
    Act Density 0.049%

    No Known Activations