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

    Neuronpedia

    INDEX
    Explanations

    mathematical notation and symbols

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     رپور
    0.37
    магази
    0.37
    诺
    0.37
    িন্দ
    0.37
    డియో
    0.36
    vironment
    0.35
    ીર
    0.35
    വോ
    0.35
    会上
    0.35
     Zamb
    0.34
    POSITIVE LOGITS
     крупных
    0.39
     Stunden
    0.39
     Ablauf
    0.38
    FLD
    0.38
     крупные
    0.37
     shortly
    0.36
     Samu
    0.35
    Ū
    0.35
     Aqui
    0.35
     besar
    0.34
    Act Density 0.002%

    No Known Activations