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

    Neuronpedia

    INDEX
    Explanations

    math problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     crowns
    -0.08
    ‍ර
    -0.08
    מבר
    -0.08
     treasured
    -0.07
     Subsequently
    -0.07
     wens
    -0.07
     crown
    -0.07
     stocks
    -0.07
    Follow
    -0.07
    ाका
    -0.07
    POSITIVE LOGITS
     empregos
    0.08
     બીજા
    0.08
     Morrison
    0.07
     Mickey
    0.07
     emplois
    0.07
     Jump
    0.07
     યુ
    0.07
     rampant
    0.07
    ardt
    0.07
    0.07
    Act Density 0.081%
    No Known Activations