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

    Neuronpedia

    INDEX
    Explanations

    TP

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     discriminate
    -0.08
     yaptı
    -0.07
     getters
    -0.07
     slaughtered
    -0.07
     superheroes
    -0.07
    뤠
    -0.06
    (encoder
    -0.06
    -pocket
    -0.06
     controversies
    -0.06
    สาย
    -0.06
    POSITIVE LOGITS
     Kul
    0.07
    ik
    0.07
    我相信
    0.07
    Paragraph
    0.07
    𝚃
    0.07
    CONDITION
    0.07
     Western
    0.06
     opportun
    0.06
     POL
    0.06
     monitoring
    0.06
    Act Density 0.001%

    No Known Activations