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

    Neuronpedia

    INDEX
    Explanations

    short bulleted list

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    <0x0D>
    0.47
    original
    0.41
    ու
    0.40
     Edit
    0.40
    こんな
    0.39
     časti
    0.38
     original
    0.38
    break
    0.38
     سوريا
    0.38
     ስ
    0.37
    POSITIVE LOGITS
     diathermy
    0.45
     disulfide
    0.42
    水素
    0.40
    esters
    0.40
     carboxylic
    0.40
    terweight
    0.40
     carbohydrate
    0.39
     cavitation
    0.39
     glutathione
    0.39
     linguistique
    0.39
    Act Density 0.000%

    No Known Activations