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

    Neuronpedia

    INDEX
    Explanations

    improvements and new versions

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     */,↵
    -0.07
    IZATION
    -0.06
    )는
    -0.06
    주
    -0.06
     DM
    -0.06
    currently
    -0.06
    ocular
    -0.06
     prioritize
    -0.06
    ={"/
    -0.05
    ینگ
    -0.05
    POSITIVE LOGITS
     Fin
    0.07
     buena
    0.07
     reluctant
    0.07
    超过
    0.07
     negate
    0.07
    ;color
    0.07
    %%%%%%%%
    0.06
    -register
    0.06
    -fin
    0.06
    棚
    0.06
    Act Density 0.371%

    No Known Activations