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

    Neuronpedia

    INDEX
    Explanations

    is followed by descriptive words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     jeopard
    0.54
     ফেলে
    0.53
    ם
    0.53
     clueless
    0.52
    기
    0.52
    ר
    0.50
    se
    0.50
    ל
    0.49
    प्या
    0.49
    Unity
    0.48
    POSITIVE LOGITS
    sla
    0.58
     পৌর
    0.54
    ról
    0.53
    ట్టిన
    0.52
    َالَ
    0.52
    力和
    0.50
     camshaft
    0.50
    aderamente
    0.50
     车
    0.50
     thóc
    0.50
    Act Density 0.000%

    No Known Activations