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

    Neuronpedia

    INDEX
    Explanations

    Math/logic proofs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    commit
    -0.07
    NULL
    -0.07
    compat
    -0.06
     canceled
    -0.06
    -vertical
    -0.06
    cr
    -0.06
    rength
    -0.06
    addons
    -0.06
     Nem
    -0.06
    mat
    -0.06
    POSITIVE LOGITS
     deneyim
    0.07
     nguồn
    0.06
     έχ
    0.06
     приблиз
    0.06
    演
    0.06
     microseconds
    0.06
    ้น
    0.06
     requestBody
    0.06
     машин
    0.06
    ighting
    0.06
    Act Density 0.045%

    No Known Activations