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

    Neuronpedia

    INDEX
    Explanations

    isoforms

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     buckle
    -0.08
     न
    -0.07
     psik
    -0.07
     ruins
    -0.07
     mie
    -0.07
     MIC
    -0.07
    	BIT
    -0.06
    PIO
    -0.06
     tally
    -0.06
    ????????????????
    -0.06
    POSITIVE LOGITS
     Đức
    0.07
    GENER
    0.06
    .Dom
    0.06
    length
    0.06
     Dorm
    0.06
    	m
    0.06
    (confirm
    0.06
    form
    0.06
    BR
    0.06
    M
    0.06
    Act Density 0.004%

    No Known Activations