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

    Neuronpedia

    INDEX
    Explanations

    presentation outline/plan

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ালো
    -0.09
    idio
    -0.08
    ২০১
    -0.08
     puse
    -0.08
    াশি
    -0.07
     izol
    -0.07
    187
    -0.07
    SUN
    -0.07
     lounges
    -0.07
     ক
    -0.07
    POSITIVE LOGITS
     purpose
    0.08
    目的
    0.08
     tujuan
    0.08
     outlining
    0.08
     उद्देश्य
    0.08
     purposes
    0.08
     angekünd
    0.08
     outlook
    0.08
     हेत
    0.08
     اهداف
    0.08
    Act Density 0.032%

    No Known Activations