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

    Neuronpedia

    INDEX
    Explanations

    math word problems

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ček
    -0.09
     adequately
    -0.08
     инвалид
    -0.08
     conducteur
    -0.08
     vänt
    -0.08
     emploi
    -0.08
     chauff
    -0.08
    ormon
    -0.07
    측
    -0.07
    _pwm
    -0.07
    POSITIVE LOGITS
     उसने
    0.09
     منهم
    0.09
     kepada
    0.09
     transferable
    0.08
     transferred
    0.08
     redistribution
    0.08
     हिस्सा
    0.08
     BB
    0.08
     giveaway
    0.08
     منها
    0.08
    Act Density 0.028%

    No Known Activations