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

    Neuronpedia

    INDEX
    Explanations

    list

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Nielsen
    -0.07
    	path
    -0.06
     Brigham
    -0.06
     Boston
    -0.06
    Boston
    -0.06
     MMA
    -0.06
     repositories
    -0.06
    桥
    -0.06
    евой
    -0.06
     ambiguous
    -0.06
    POSITIVE LOGITS
    	list
    0.07
    _country
    0.07
    .RESULT
    0.07
    _KERNEL
    0.07
     привед
    0.07
    —
    0.06
    안마
    0.06
    ��
    0.06
    _Release
    0.06
    ับน
    0.06
    Act Density 0.036%

    No Known Activations