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

    Neuronpedia

    INDEX
    Explanations

    Legal disclaimers

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;:
    -0.08
    '));
    -0.07
    )','
    -0.07
    	write
    -0.07
    ')}
    -0.06
     predictor
    -0.06
     vám
    -0.06
    movie
    -0.06
     чаще
    -0.06
    ]);
↵
↵
    -0.06
    POSITIVE LOGITS
    udes
    0.06
     fou
    0.06
    ANO
    0.06
    Empleado
    0.06
    як
    0.06
     As
    0.06
    -chat
    0.06
     influences
    0.06
    �
    0.06
    ्तक
    0.06
    Act Density 0.004%

    No Known Activations