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

    Neuronpedia

    INDEX
    Explanations

    essential for

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    힐
    0.45
     устро
    0.44
     specializes
    0.42
     Waffen
    0.42
    getExternal
    0.42
    走
    0.42
    、《
    0.40
     избра
    0.40
    理論
    0.40
    時
    0.39
    POSITIVE LOGITS
     hatta
    0.56
    <unused2141>
    0.50
     după
    0.49
     kik
    0.48
     asla
    0.48
    as
    0.48
    因为它
    0.47
    slan
    0.47
    ceral
    0.46
     کیونکہ
    0.46
    Act Density 0.001%

    No Known Activations