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

    Neuronpedia

    INDEX
    Explanations

    #

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    oop
    -0.06
    grid
    -0.06
     corrobor
    -0.06
    -parse
    -0.06
    ीवन
    -0.06
    odos
    -0.06
    /actions
    -0.06
    ược
    -0.06
    ayıp
    -0.06
    ický
    -0.06
    POSITIVE LOGITS
     reserv
    0.07
     předpis
    0.06
     tj
    0.06
     verge
    0.06
     fuse
    0.06
     dipping
    0.06
     كيف
    0.06
     incentives
    0.06
     investigate
    0.06
     lose
    0.06
    Act Density 0.001%

    No Known Activations