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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     تحصیل
    -0.07
    .Cancel
    -0.07
     پا
    -0.07
     suites
    -0.06
    998
    -0.06
    шла
    -0.06
     입력
    -0.06
     Ста
    -0.06
    710
    -0.06
    Exactly
    -0.06
    POSITIVE LOGITS
    ARENT
    0.07
    .setInt
    0.06
    (rowIndex
    0.06
    rema
    0.06
    �ng
    0.06
     appet
    0.06
    oge
    0.06
     gerç
    0.06
    ocode
    0.06
    (alpha
    0.06
    Act Density 0.006%

    No Known Activations