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

    Neuronpedia

    INDEX
    Explanations

    to be

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     that
    0.57
     which
    0.51
    that
    0.50
     any
    0.47
     whiche
    0.45
     streamlining
    0.44
     Any
    0.42
    one
    0.42
     using
    0.42
     YAML
    0.42
    POSITIVE LOGITS
    送料無料
    0.44
     प्रचंड
    0.42
     воен
    0.41
     ג
    0.40
     ס
    0.39
    ד
    0.39
     devast
    0.39
     suscit
    0.39
     stagione
    0.38
    ドレス
    0.38
    Act Density 0.040%

    No Known Activations