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

    Neuronpedia

    INDEX
    Explanations

    f

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ᨾ
    -0.08
     doping
    -0.07
    纪检
    -0.07
     TextInputType
    -0.07
     Châu
    -0.07
     질
    -0.07
    LINE
    -0.06
     morb
    -0.06
     UIAlertController
    -0.06
     ApplicationUser
    -0.06
    POSITIVE LOGITS
    .per
    0.08
    0.08
     wash
    0.07
    美国人
    0.06
    .mas
    0.06
    aways
    0.06
    坎
    0.06
    --------
    0.06
    posts
    0.06
    0.06
    Act Density 0.003%

    No Known Activations