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

    Neuronpedia

    INDEX
    Explanations

    three

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ир
    -0.07
    Attribute
    -0.07
    	My
    -0.07
    Entre
    -0.07
    Thumbnail
    -0.07
    -"
    -0.07
     Friedman
    -0.06
    Destroy
    -0.06
    。她
    -0.06
    InvalidArgumentException
    -0.06
    POSITIVE LOGITS
     proved
    0.06
     trophies
    0.06
     proficient
    0.06
    득
    0.06
    ترل
    0.06
     Upgrade
    0.06
     interpre
    0.06
    qualified
    0.06
     ви
    0.05
    альної
    0.05
    Act Density 0.008%

    No Known Activations