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

    Neuronpedia

    INDEX
    Explanations

    sch

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .matmul
    -0.07
    eut
    -0.07
    ?>>
    -0.07
    -HT
    -0.07
    jed
    -0.07
    gett
    -0.07
     TESTING
    -0.06
     Jest
    -0.06
     obt
    -0.06
    vature
    -0.06
    POSITIVE LOGITS
     dish
    0.07
    -trigger
    0.07
    .panel
    0.07
     singing
    0.06
     among
    0.06
    _cleanup
    0.06
     curse
    0.06
     """↵↵
    0.06
    	Buffer
    0.06
    -sponsored
    0.06
    Act Density 0.014%

    No Known Activations