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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     fos
    -0.08
    decor
    -0.07
    _ang
    -0.06
     roads
    -0.06
     gel
    -0.06
     pis
    -0.06
     MessageType
    -0.06
    抗
    -0.06
     bu
    -0.06
    Convert
    -0.06
    POSITIVE LOGITS
    /Common
    0.07
    owment
    0.06
     advisor
    0.06
     Middle
    0.06
    огра
    0.06
     расход
    0.06
    aturity
    0.06
     özelliği
    0.06
     Anc
    0.06
     Breast
    0.06
    Act Density 0.065%

    No Known Activations