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

    Neuronpedia

    INDEX
    Explanations

    same

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     yielded
    -0.08
     pipelines
    -0.08
     liners
    -0.07
     Rivers
    -0.07
    <A
    -0.07
     argent
    -0.07
     stunned
    -0.07
    (iterator
    -0.07
    二是
    -0.07
     PSI
    -0.07
    POSITIVE LOGITS
    举
    0.08
    彷
    0.07
    Notes
    0.07
     эти
    0.07
     dil
    0.07
    팰
    0.06
    巍
    0.06
    盈利能力
    0.06
    볐
    0.06
     POSSIBILITY
    0.06
    Act Density 0.011%

    No Known Activations