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

    Neuronpedia

    INDEX
    Explanations

    Numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    965
    -0.07
    xp
    -0.07
     Savior
    -0.06
    	sd
    -0.06
    :i
    -0.06
    nob
    -0.06
    Steven
    -0.06
     eventual
    -0.06
     vl
    -0.06
    high
    -0.06
    POSITIVE LOGITS
     ostat
    0.08
     establishing
    0.07
    ноп
    0.06
     öncelik
    0.06
     uzav
    0.06
    alarda
    0.06
    want
    0.06
     slew
    0.06
     бесп
    0.06
    aya
    0.06
    Act Density 0.013%

    No Known Activations