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

    Neuronpedia

    INDEX
    Explanations

    space

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     culturally
    -0.10
    (exchange
    -0.08
     refresh
    -0.08
     consultant
    -0.08
     culturel
    -0.08
     politically
    -0.08
     culturelle
    -0.08
    cer
    -0.08
     जाग
    -0.07
     latin
    -0.07
    POSITIVE LOGITS
     Quadr
    0.09
     નિવ
    0.08
     Cartesian
    0.08
    际
    0.08
    Quadr
    0.08
     સમ
    0.08
     quadr
    0.07
    phant
    0.07
    ীয়
    0.07
     allegation
    0.07
    Act Density 0.003%

    No Known Activations