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

    Neuronpedia

    INDEX
    Explanations

    specific descriptions or papers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    posing
    0.50
     concess
    0.44
    <0xB0>
    0.44
    posed
    0.43
     zoon
    0.42
    CreatedAt
    0.41
     COX
    0.41
    ライズ
    0.41
    Set
    0.40
     AUD
    0.40
    POSITIVE LOGITS
    ل
    0.52
    یک
    0.50
    ভের
    0.47
    لک
    0.46
    ᵔ
    0.46
    িমের
    0.46
    žić
    0.46
    רק
    0.45
     angelic
    0.44
     Fus
    0.44
    Act Density 0.002%

    No Known Activations