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

    Neuronpedia

    INDEX
    Explanations

    code formatting

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Change
    -0.06
     kilomet
    -0.06
    퓨
    -0.06
    PLIER
    -0.06
     सद
    -0.06
    ept
    -0.06
    fraction
    -0.06
    Signed
    -0.06
    .drive
    -0.06
    τοκ
    -0.06
    POSITIVE LOGITS
     lässt
    0.07
    #endregion
    0.07
    (cell
    0.07
     economic
    0.07
     ιστο
    0.06
     contributions
    0.06
    ]bool
    0.06
     學
    0.06
     QtAws
    0.06
    rebbe
    0.06
    Act Density 0.000%

    No Known Activations