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

    Neuronpedia

    INDEX
    Explanations

    equals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    	exp
    -0.07
    _Port
    -0.07
     Pag
    -0.06
     �
    -0.06
     getColumn
    -0.06
    ちょ
    -0.06
    !).↵↵
    -0.06
    tres
    -0.06
     ostr
    -0.06
     dut
    -0.06
    POSITIVE LOGITS
    =\
    0.09
    )=
    0.08
    }=
    0.07
     Michel
    0.07
    =request
    0.06
     hely
    0.06
     =
    0.06
     Profiles
    0.06
    ={(
    0.06
    rysler
    0.06
    Act Density 0.013%

    No Known Activations