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

    Neuronpedia

    INDEX
    Explanations

    Scientific/technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    744
    -0.07
    bling
    -0.07
    abc
    -0.06
     investor
    -0.06
    /the
    -0.06
     Burl
    -0.06
    FromString
    -0.06
     approve
    -0.06
     interven
    -0.06
    unda
    -0.06
    POSITIVE LOGITS
     dental
    0.06
    .floor
    0.06
     flaws
    0.06
     searchText
    0.06
     understandably
    0.06
    ，↵↵
    0.06
    �
    0.06
     arbe
    0.06
     noe
    0.06
    PO
    0.05
    Act Density 0.058%

    No Known Activations