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

    Neuronpedia

    INDEX
    Explanations

    positive definite matrix

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    گی
    0.54
     adhesions
    0.54
     sweating
    0.53
     hills
    0.52
     eyelashes
    0.52
    aneous
    0.52
    вання
    0.52
    ని
    0.51
     glycolysis
    0.51
     уровень
    0.51
    POSITIVE LOGITS
    1
    0.54
    稍
    0.52
    HTC
    0.48
    稍微
    0.47
    比較
    0.47
    RO
    0.46
    イルス
    0.46
    คุ
    0.46
    Tag
    0.46
    tag
    0.45
    Act Density 0.000%

    No Known Activations