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

    Neuronpedia

    INDEX
    Explanations

    ..

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    fraction
    -0.08
    .proj
    -0.07
     maximal
    -0.06
    _sell
    -0.06
    -box
    -0.06
     Werner
    -0.06
     Charity
    -0.06
    _kw
    -0.06
    	set
    -0.06
    zeros
    -0.06
    POSITIVE LOGITS
    ="../
    0.07
    ("~/
    0.07
    _enc
    0.07
     institutions
    0.07
     %@",
    0.06
    %@",
    0.06
    (pp
    0.06
    (In
    0.06
     nave
    0.06
    oolStrip
    0.06
    Act Density 0.004%

    No Known Activations