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

    Neuronpedia

    INDEX
    Explanations

    if or will

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     genetic
    0.26
    OLOGICAL
    0.26
     socio
    0.25
    2
    0.25
    ことに
    0.24
     κοινων
    0.24
     biological
    0.24
    :
    0.24
     community
    0.23
     embodiments
    0.23
    POSITIVE LOGITS
     увеличи
    0.30
     sadece
    0.28
     바꾸
    0.28
     tetap
    0.28
     zů
    0.28
    扪
    0.28
    ţi
    0.28
    畱
    0.28
     лиш
    0.27
    蓦
    0.27
    Act Density 0.000%

    No Known Activations