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

    Neuronpedia

    INDEX
    Explanations

    CSS utility classes with hyphens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.51
     siguientes
    0.44
    ក់
    0.42
    ută
    0.42
    ᆸ
    0.40
    ાસ
    0.40
     ŝ
    0.40
    ала
    0.40
    ח
    0.39
     poudre
    0.39
    POSITIVE LOGITS
    -
    0.55
    _
    0.46
    -${
    0.44
    $-
    0.41
    [-
    0.41
    -"
    0.40
    0.40
     ඔහු
    0.39
    -%
    0.39
    ־
    0.39
    Act Density 0.008%

    No Known Activations