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

    Neuronpedia

    INDEX
    Explanations

    red oceans

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     drawRight
    0.55
     councillor
    0.50
    Ꮼ
    0.49
    iply
    0.46
     counsellor
    0.45
    anjut
    0.45
    ayang
    0.45
    ൃശ
    0.44
    িকা
    0.43
    avk
    0.43
    POSITIVE LOGITS
    ی
    0.50
    s
    0.48
    ंचे
    0.47
     ascenso
    0.46
    ته
    0.45
    ים
    0.44
     ascent
    0.44
    했지만
    0.43
     rộng
    0.40
     संदर्भित
    0.40
    Act Density 0.001%

    No Known Activations