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

    Neuronpedia

    INDEX
    Explanations

    formed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    riends
    -0.06
     Coc
    -0.06
    .Absolute
    -0.06
    iqu
    -0.06
     evac
    -0.06
    zeros
    -0.06
    _Back
    -0.06
     dude
    -0.06
    .ASCII
    -0.06
     files
    -0.06
    POSITIVE LOGITS
    obra
    0.07
    _fmt
    0.07
    invert
    0.06
    /class
    0.06
    Lifecycle
    0.06
    �
    0.06
     offsetof
    0.06
    는데
    0.06
     Cran
    0.06
    。',↵
    0.06
    Act Density 0.044%

    No Known Activations