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

    Neuronpedia

    INDEX
    Explanations

    critiques of societal issues

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     истории
    -0.07
     '?'
    -0.07
     convex
    -0.06
    energy
    -0.06
    nutím
    -0.06
    /R
    -0.06
    ("\(
    -0.06
     aeros
    -0.06
    .ToShort
    -0.06
     datetime
    -0.06
    POSITIVE LOGITS
    .getCurrent
    0.07
     gentle
    0.06
    観
    0.06
     directs
    0.06
     ami
    0.06
     hypo
    0.06
     RDF
    0.06
    προ
    0.06
     conse
    0.06
    Κ
    0.06
    Act Density 0.019%

    No Known Activations