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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    서
    -0.08
     Mayo
    -0.07
     edit
    -0.07
    ブ
    -0.07
     brasileiras
    -0.07
     Southeastern
    -0.07
    );
↵/
    -0.07
     Grove
    -0.07
     lus
    -0.07
    ключ
    -0.07
    POSITIVE LOGITS
     inferred
    0.12
     implied
    0.09
     assumed
    0.08
     deducted
    0.08
     Infer
    0.08
    Inference
    0.08
     ded
    0.08
     guessed
    0.08
    _imp
    0.08
     জানা
    0.08
    Act Density 0.129%

    No Known Activations