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

    Neuronpedia

    INDEX
    Explanations

    oles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     overwritten
    -0.08
     terrorist
    -0.07
     Ish
    -0.07
    ම්
    -0.07
     Claire
    -0.07
    ICES
    -0.07
    త
    -0.07
    ిస్తున్న
    -0.07
    นะนำ
    -0.07
     leest
    -0.07
    POSITIVE LOGITS
     واحدة
    0.09
     ane
    0.09
     dys
    0.08
    .Metadata
    0.07
     ale
    0.07
     jed
    0.07
     المطل
    0.07
     especific
    0.07
     nu
    0.07
     interconnected
    0.07
    Act Density 0.003%

    No Known Activations