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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     superintendent
    -0.06
    -Pack
    -0.06
    ⌒
    -0.06
     ">↵
    -0.06
     ButterKnife
    -0.06
    یت
    -0.06
    ılığıyla
    -0.06
    โอ
    -0.06
     якого
    -0.06
     missiles
    -0.06
    POSITIVE LOGITS
    undefined
    0.07
     legit
    0.07
    GMT
    0.07
    Beta
    0.06
    acho
    0.06
     підстав
    0.06
    云
    0.06
     POL
    0.06
     exerc
    0.06
     Prescott
    0.06
    Act Density 0.031%

    No Known Activations