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

    Neuronpedia

    INDEX
    Explanations

    technical terms and processes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    "/>.
    0.61
     ذریع
    0.59
    یں۔
    0.56
    }.
    0.55
    ។
    0.55
    ).
    0.54
    》。
    0.53
    ।
    0.53
    。
    0.52
    ’।
    0.51
    POSITIVE LOGITS
     is
    0.57
     has
    0.53
     seems
    0.51
     remains
    0.48
     bukanlah
    0.44
     could
    0.43
     otrzyma
    0.43
    താണ്
    0.42
     appears
    0.42
     está
    0.41
    Act Density 0.080%

    No Known Activations