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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ประก
    -0.08
     Fraser
    -0.07
     frem
    -0.07
     surged
    -0.07
     Jeg
    -0.06
     pedestal
    -0.06
     �
    -0.06
    regions
    -0.06
     Comedy
    -0.06
     Ін
    -0.06
    POSITIVE LOGITS
     "--
    0.08
    (instruction
    0.08
     InkWell
    0.07
     *)↵
    0.07
     notifying
    0.07
    _from
    0.07
     cuda
    0.06
    521
    0.06
    _WITH
    0.06
     NSNumber
    0.06
    Act Density 0.023%

    No Known Activations