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

    Neuronpedia

    INDEX
    Explanations

    sustainability

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    568
    -0.07
    CONS
    -0.07
    plug
    -0.06
    (height
    -0.06
    ewith
    -0.06
     stoi
    -0.06
    .writ
    -0.06
    ova
    -0.06
    joint
    -0.06
    .AsyncTask
    -0.06
    POSITIVE LOGITS
    亜
    0.07
    -doc
    0.06
    _tolerance
    0.06
    _TYPES
    0.06
     >↵
    0.06
    �
    0.06
    頁
    0.06
     ціка
    0.06
    Currently
    0.06
    -confidence
    0.06
    Act Density 0.044%

    No Known Activations