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

    Neuronpedia

    INDEX
    Explanations

    |

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    eli
    -0.06
    Static
    -0.06
     Phone
    -0.06
    	delete
    -0.06
    unt
    -0.06
     Guardian
    -0.06
    _templates
    -0.06
    ыџN
    -0.05
    iframe
    -0.05
    ��
    -0.05
    POSITIVE LOGITS
     instancia
    0.07
     playwright
    0.07
     Sala
    0.07
     piled
    0.07
    gua
    0.07
    caps
    0.07
     GAP
    0.06
     사무
    0.06
     дина
    0.06
    [arr
    0.06
    Act Density 0.000%

    No Known Activations