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

    Neuronpedia

    INDEX
    Explanations

    core principle of operation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     aborted
    0.48
    可能是
    0.43
     elaboration
    0.41
    ких
    0.39
    gem
    0.38
    सिल
    0.38
     delimiter
    0.38
     UML
    0.38
     cleanup
    0.38
     precise
    0.38
    POSITIVE LOGITS
     esencia
    0.44
     суть
    0.44
     inscreva
    0.44
    原理
    0.43
     ramai
    0.43
     historie
    0.42
     funcionamiento
    0.41
     тут
    0.40
     funcionando
    0.40
     teoría
    0.39
    Act Density 0.001%

    No Known Activations