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

    Neuronpedia

    INDEX
    Explanations

    only

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .pages
    -0.07
     pane
    -0.07
    Italic
    -0.06
     circulated
    -0.06
    ülen
    -0.06
    Bu
    -0.06
     drama
    -0.06
    	files
    -0.06
    (mode
    -0.06
     zpráv
    -0.06
    POSITIVE LOGITS
     only
    0.07
    lude
    0.07
    餐
    0.07
     Maxim
    0.06
     artisans
    0.06
    Minimal
    0.06
    PUTE
    0.06
    tracer
    0.06
     MET
    0.06
    _DYNAMIC
    0.06
    Act Density 0.017%

    No Known Activations