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

    Neuronpedia

    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jackson
    -0.07
    िछल
    -0.07
    -media
    -0.06
     "../
    -0.06
     zoals
    -0.06
    ycling
    -0.06
    iotic
    -0.06
    гля
    -0.06
     Bradley
    -0.06
    任何
    -0.06
    POSITIVE LOGITS
    	AM
    0.08
    身上
    0.07
    کز
    0.07
     notify
    0.07
     To
    0.07
    To
    0.06
     trem
    0.06
     prepared
    0.06
     astr
    0.06
    -parser
    0.06
    Act Density 0.092%

    No Known Activations