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

    Neuronpedia

    INDEX
    Explanations

    ant

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ，用
    -0.07
    Borders
    -0.06
     Axios
    -0.06
    Articles
    -0.06
     Код
    -0.06
     elsewhere
    -0.06
     speaker
    -0.06
    232
    -0.06
    iliki
    -0.06
    宣
    -0.06
    POSITIVE LOGITS
    (pc
    0.07
     ntohs
    0.07
    líč
    0.07
    [node
    0.07
    _SOFT
    0.06
    [char
    0.06
    tsky
    0.06
    ček
    0.06
    องท
    0.06
    нимает
    0.06
    Act Density 0.003%

    No Known Activations