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

    Neuronpedia

    INDEX
    Explanations

    cord, codeword, cards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     viscosity
    0.46
    leValue
    0.45
    無視
    0.43
     Fuk
    0.43
    Expected
    0.43
     viscos
    0.42
     solvency
    0.40
    張り
    0.39
    linge
    0.39
     Dalib
    0.38
    POSITIVE LOGITS
     Houd
    0.41
    Cord
    0.40
     cord
    0.40
    cord
    0.39
    Notebook
    0.39
    xl
    0.36
    家庭
    0.36
     Cord
    0.36
     cords
    0.36
    cod
    0.35
    Act Density 0.004%

    No Known Activations