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

    Neuronpedia

    INDEX
    Explanations

    flexible movement and operating results

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     permissive
    0.47
     the
    0.45
     SSL
    0.44
     intermediaries
    0.44
     e
    0.43
     oss
    0.42
     Katz
    0.42
     (
    0.41
     be
    0.41
     obso
    0.40
    POSITIVE LOGITS
    住院
    0.53
     cómoda
    0.51
    이가
    0.51
    രിക്കുന്ന
    0.51
     teléfono
    0.50
    项目的
    0.49
    überkü
    0.49
    鍱
    0.49
     cómod
    0.49
    дона
    0.49
    Act Density 0.000%

    No Known Activations