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

    Neuronpedia

    INDEX
    Explanations

    single quotes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Navigation
    -0.07
     GRAT
    -0.07
     FETCH
    -0.07
     married
    -0.07
    .btnDelete
    -0.07
     encode
    -0.07
     IOException
    -0.07
    _change
    -0.07
     among
    -0.07
    imuth
    -0.06
    POSITIVE LOGITS
    ◆
    0.07
    े.
    0.06
     erot
    0.06
     disillusion
    0.06
     حالی
    0.06
    pon
    0.06
    aaaaaaaa
    0.06
    μένοι
    0.06
    학기
    0.06
    견
    0.06
    Act Density 0.003%

    No Known Activations