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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    [contains
    -0.07
    _ste
    -0.07
    parameters
    -0.07
                                        ↵
    -0.07
    ymmetric
    -0.07
     wound
    -0.06
     Comfort
    -0.06
     patio
    -0.06
    incoming
    -0.06
     التي
    -0.06
    POSITIVE LOGITS
    	struct
    0.07
     �
    0.07
     eğit
    0.06
     SPEC
    0.06
     EX
    0.06
    -backed
    0.06
     ＿
    0.06
    itet
    0.06
    _:
    0.06
     떨어
    0.06
    Act Density 0.000%

    No Known Activations