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

    Neuronpedia

    INDEX
    Explanations

    Problems/Negativity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dynamics
    -0.06
    	f
    -0.06
     ры
    -0.06
    Trees
    -0.06
     transformative
    -0.06
    }`}↵
    -0.06
     Když
    -0.06
     okay
    -0.06
    Když
    -0.06
    腕
    -0.06
    POSITIVE LOGITS
    chat
    0.07
    rahim
    0.07
     withheld
    0.06
    ิช
    0.06
     calf
    0.06
    lage
    0.06
     Madden
    0.06
    WT
    0.06
     Jame
    0.06
    aptured
    0.06
    Act Density 0.000%

    No Known Activations