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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     derivative
    -0.06
    roof
    -0.06
    ρεί
    -0.06
     strives
    -0.06
    unit
    -0.06
    elts
    -0.06
     ass
    -0.06
    bilt
    -0.06
    ounce
    -0.06
    ころ
    -0.06
    POSITIVE LOGITS
    。',↵
    0.07
    、↵↵
    0.07
     BEN
    0.07
     ''↵↵
    0.06
     _
↵
    0.06
     delle
    0.06
    -sidebar
    0.06
    ..."↵
    0.06
    'l
    0.06
     أحد
    0.06
    Act Density 0.001%

    No Known Activations