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

    Neuronpedia

    INDEX
    Explanations

    /DTD

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _depend
    -0.06
    تی
    -0.06
     alta
    -0.06
     identifying
    -0.06
    (...
    -0.06
    .Tab
    -0.06
     parler
    -0.06
    ерт
    -0.06
     Topics
    -0.06
    ог
    -0.06
    POSITIVE LOGITS
    Indexes
    0.07
    ulfill
    0.07
    /DTD
    0.07
    .SUB
    0.07
    Reviews
    0.06
     �
    0.06
    ...↵↵↵↵
    0.06
     Clippers
    0.06
    enderror
    0.06
     inaccurate
    0.06
    Act Density 0.001%

    No Known Activations