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

    Neuronpedia

    INDEX
    Explanations

    else conditional branches

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     non
    0.48
     jerry
    0.41
     &
    0.40
     caso
    0.40
     cases
    0.39
     hops
    0.39
    &
    0.39
     virtual
    0.38
     Contr
    0.37
    polyfills
    0.37
    POSITIVE LOGITS
     غلط
    0.41
    TION
    0.40
    톄
    0.39
    อื่น
    0.38
     गलत
    0.38
    ونو
    0.37
     ভুল
    0.37
    Mogo
    0.36
    Anything
    0.36
     किसी
    0.36
    Act Density 0.011%

    No Known Activations