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

    Neuronpedia

    INDEX
    Explanations

    Sentence boundaries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     guardians
    -0.07
    422
    -0.06
     Floral
    -0.06
    DESCRIPTION
    -0.06
     Exped
    -0.06
     Purple
    -0.06
     EX
    -0.06
    �
    -0.06
    /de
    -0.06
     Gur
    -0.06
    POSITIVE LOGITS
     Tes
    0.06
    (Properties
    0.06
     τρα
    0.06
     ép
    0.06
    [MAX
    0.06
    otic
    0.06
     Gros
    0.06
    цеп
    0.06
    ester
    0.06
     corpor
    0.06
    Act Density 0.063%

    No Known Activations