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

    Neuronpedia

    INDEX
    Explanations

    C++ data types and containers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    കൊ
    0.84
    tiempo
    0.82
     após
    0.81
     gracias
    0.80
     atención
    0.78
     nú
    0.76
     después
    0.76
     filho
    0.75
     tiempo
    0.74
     Pronto
    0.73
    POSITIVE LOGITS
    &
    1.44
    &&
    1.13
    \&
    1.02
     &
    1.01
    &-
    0.83
    >&
    0.83
    $&
    0.80
    +
    0.78
    }&
    0.78
    =&
    0.76
    Act Density 0.044%

    No Known Activations