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

    Neuronpedia

    INDEX
    Explanations

    these

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (config
    -0.07
    Modal
    -0.07
    Retry
    -0.07
    542
    -0.06
     Argument
    -0.06
    stype
    -0.06
    ortality
    -0.06
    Bright
    -0.06
    (geometry
    -0.06
    	mysqli
    -0.06
    POSITIVE LOGITS
     Něk
    0.07
     airline
    0.06
     Igor
    0.06
     چ
    0.06
     KH
    0.06
     ماند
    0.06
     Germans
    0.06
    ANGE
    0.06
     Er
    0.06
    ��
    0.06
    Act Density 0.360%

    No Known Activations