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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    catch
    -0.08
    -0.07
     fabricated
    -0.07
     transversal
    -0.07
    ymy
    -0.07
     proced
    -0.07
    ng
    -0.07
    _pm
    -0.07
     described
    -0.07
     two
    -0.07
    POSITIVE LOGITS
     infatti
    0.08
     Jeans
    0.08
     छो
    0.08
     아닌
    0.08
     zaten
    0.08
     छ
    0.08
     जाण
    0.08
     winger
    0.08
     oldal
    0.08
    ehicles
    0.08
    Act Density 0.115%
    No Known Activations