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

    Neuronpedia

    INDEX
    Explanations

    extract

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    arrays
    -0.07
    确认
    -0.06
    Eat
    -0.06
     "+
    -0.06
     risking
    -0.06
     Eat
    -0.06
    hamster
    -0.06
    exion
    -0.06
     �
    -0.06
    aware
    -0.06
    POSITIVE LOGITS
    egra
    0.07
    mass
    0.06
    patients
    0.06
    riel
    0.06
    subpackage
    0.06
    _rom
    0.06
    _extraction
    0.06
     Mey
    0.06
    autom
    0.06
    '",↵
    0.06
    Act Density 0.014%

    No Known Activations