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

    Neuronpedia

    INDEX
    Explanations

    code or technical writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ivr
    -0.08
    Friendly
    -0.06
     هناك
    -0.06
    �
    -0.06
    approve
    -0.06
     Biggest
    -0.06
    ین
    -0.06
     постро
    -0.06
    вается
    -0.06
    ателей
    -0.06
    POSITIVE LOGITS
     Comic
    0.08
    IFI
    0.08
    .Character
    0.07
     Lat
    0.07
     salv
    0.07
     toddler
    0.07
     commands
    0.06
    =device
    0.06
    =*
    0.06
     perror
    0.06
    Act Density 0.001%

    No Known Activations