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

    Neuronpedia

    INDEX
    Explanations

    around

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Validator
    -0.07
    engl
    -0.06
     Fol
    -0.06
     Activ
    -0.06
     vida
    -0.06
    (filtered
    -0.06
    ’à
    -0.06
     IDF
    -0.06
     мови
    -0.06
     菲
    -0.06
    POSITIVE LOGITS
    marker
    0.08
    род
    0.06
    大人
    0.06
    className
    0.06
     acronym
    0.06
     nedenle
    0.06
    ling
    0.06
    pointer
    0.06
    alom
    0.06
    %D
    0.06
    Act Density 0.006%

    No Known Activations