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

    Neuronpedia

    INDEX
    Explanations

    states and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    শ্র
    0.72
    ளவு
    0.71
     nying
    0.69
    anso
    0.69
     ανθ
    0.68
     piracy
    0.67
    aco
    0.67
     sức
    0.67
     வரலாற்று
    0.67
     हर्ष
    0.67
    POSITIVE LOGITS
    ness
    1.67
     status
    1.65
    Status
    1.53
    status
    1.40
     상태
    1.34
     بودن
    1.33
     Status
    1.33
     статус
    1.25
    NESS
    1.21
    状态
    1.15
    Act Density 0.485%

    No Known Activations