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

    Neuronpedia

    INDEX
    Explanations

    proteins and RNA

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    उदाहरण
    0.52
    ସ୍
    0.51
    ご
    0.47
    го
    0.46
    現在
    0.46
     behov
    0.45
    рее
    0.45
    𝐞
    0.45
     processo
    0.44
    伺
    0.44
    POSITIVE LOGITS
    ają
    0.56
     as
    0.54
     ",
    0.47
     ∈
    0.46
    ،
    0.46
     "):
    0.46
     ".
    0.45
    ulam
    0.45
    uw
    0.45
     amended
    0.44
    Act Density 0.000%

    No Known Activations