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

    Neuronpedia

    INDEX
    Explanations

    Website documents and resources

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IMUM
    -0.07
     весь
    -0.06
     Face
    -0.06
     questions
    -0.06
     humanities
    -0.06
     Therefore
    -0.06
    regions
    -0.06
    $num
    -0.06
     Humanities
    -0.06
    Therefore
    -0.06
    POSITIVE LOGITS
     [\
    0.07
    (te
    0.07
    ▏
    0.07
    ligne
    0.06
    petto
    0.06
    )(__
    0.06
    ("--------------------------------
    0.06
     �
    0.06
    (local
    0.06
    	RTDBG
    0.06
    Act Density 0.108%

    No Known Activations