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

    Neuronpedia

    INDEX
    Explanations

    Ionic columns

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     trials
    -0.07
    說
    -0.06
    '),↵
    -0.06
     widths
    -0.06
    (),
↵
    -0.06
     premises
    -0.06
     Lists
    -0.06
     talked
    -0.06
    普
    -0.06
    σια
    -0.06
    POSITIVE LOGITS
    -д
    0.06
    362
    0.06
     somew
    0.06
    -valu
    0.06
    688
    0.06
    -console
    0.06
    (getClass
    0.06
    _Selection
    0.06
    legates
    0.06
    /sys
    0.06
    Act Density 0.008%

    No Known Activations