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

    Neuronpedia

    INDEX
    Explanations

    Symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     drop
    -0.06
    Github
    -0.06
     greens
    -0.06
    ура
    -0.06
    怀
    -0.05
     Whereas
    -0.05
    emás
    -0.05
     canyon
    -0.05
     Nationals
    -0.05
    イン
    -0.05
    POSITIVE LOGITS
    _SCR
    0.07
    /
↵
    0.07
     rukou
    0.06
    gesch
    0.06
    [action
    0.06
    ocache
    0.06
    'aff
    0.06
    んだ
    0.06
    âk
    0.06
    دهای
    0.06
    Act Density 0.016%

    No Known Activations