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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    :title
    -0.07
     lineup
    -0.07
     Roger
    -0.06
     Avery
    -0.06
    azer
    -0.06
     CDN
    -0.06
    MaxY
    -0.06
     moist
    -0.06
    IVA
    -0.06
    @testable
    -0.06
    POSITIVE LOGITS
     дви
    0.06
     unarmed
    0.06
     піс
    0.06
    ско
    0.06
    ؤال
    0.06
     cle
    0.06
    том
    0.06
     sty
    0.06
     yeah
    0.06
    osphere
    0.05
    Act Density 0.014%

    No Known Activations