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

    Neuronpedia

    INDEX
    Explanations

    i

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     headphone
    -0.07
    ిస్తుంది
    -0.07
    (`
    -0.07
     ment
    -0.07
     brownies
    -0.07
     mentoring
    -0.07
     cartridge
    -0.07
    ിച്ചിട്ടുണ്ട്
    -0.07
    Throttle
    -0.07
     aspectos
    -0.07
    POSITIVE LOGITS
     clockwise
    0.09
     cyclic
    0.09
     cyc
    0.09
    #__
    0.08
     Lena
    0.08
    :
↵
    0.08
     circular
    0.08
    ями
    0.08
    :
↵
↵
    0.08
    amat
    0.08
    Act Density 0.009%

    No Known Activations