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

    Neuronpedia

    INDEX
    Explanations

    уч

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    👔
    -0.08
     murderer
    -0.08
    吐槽
    -0.07
    (itr
    -0.07
     משר
    -0.07
     tiled
    -0.07
     Cyr
    -0.07
     spins
    -0.07
     prakt
    -0.07
    旅行
    -0.07
    POSITIVE LOGITS
     clam
    0.07
    .Pass
    0.06
     Learning
    0.06
    nodiscard
    0.06
    합니다
    0.06
     RPM
    0.06
    _;↵
    0.06
    (example
    0.06
    jem
    0.06
    heet
    0.06
    Act Density 0.004%

    No Known Activations