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

    Neuronpedia

    INDEX
    Explanations

    Scientific articles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BOX
    -0.07
     Breakfast
    -0.07
    675
    -0.06
     implies
    -0.06
    を使
    -0.06
    document
    -0.06
     errores
    -0.06
    ापस
    -0.06
     cartoon
    -0.06
    -ни
    -0.06
    POSITIVE LOGITS
    کز
    0.06
     Dota
    0.06
    ,t
    0.06
     údaj
    0.06
    amas
    0.06
    Fair
    0.06
    wk
    0.06
    Certificates
    0.06
     *&
    0.05
    (mapped
    0.05
    Act Density 0.045%

    No Known Activations