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

    Neuronpedia

    INDEX
    Explanations

    jumping the gun; out of the box

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    forEach
    0.42
    OrderFlight
    0.42
    the
    0.42
     samano
    0.42
     nastav
    0.41
     tortues
    0.40
    ORUS
    0.40
     filha
    0.40
     daž
    0.39
     nemmeno
    0.39
    POSITIVE LOGITS
    0.49
    <
    0.47
    ?
    0.45
    し
    0.42
    ^
    0.41
    F
    0.41
    ции
    0.41
    *
    0.41
    -
    0.41
    >
    0.40
    Act Density 0.003%

    No Known Activations