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

    Neuronpedia

    INDEX
    Explanations

    proportion of a substance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    =\{
    0.36
    lop
    0.34
    膝
    0.34
    нын
    0.34
     Lop
    0.33
    ]=-
    0.32
     হয়ত
    0.31
    =\
    0.31
    ="-
    0.30
    atthe
    0.30
    POSITIVE LOGITS
     `<`,
    0.35
    startswith
    0.33
     }>;
    0.33
     prevented
    0.33
    אין
    0.32
     for
    0.32
     disrupts
    0.32
     central
    0.32
    ᗜ
    0.32
     creates
    0.31
    Act Density 0.001%

    No Known Activations