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

    Neuronpedia

    INDEX
    Explanations

    request parts: body, params, query, headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ҹ
    0.40
    姏
    0.40
    WHM
    0.40
    eosin
    0.39
     осе
    0.39
    aptop
    0.39
    㣻
    0.39
    蛳
    0.38
     нанесе
    0.38
    ণাস্ত্র
    0.38
    POSITIVE LOGITS
     params
    0.88
     body
    0.86
    params
    0.84
     Params
    0.81
    body
    0.77
    Params
    0.74
     Body
    0.70
    query
    0.69
     headers
    0.68
    Body
    0.66
    Act Density 0.008%

    No Known Activations