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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    issional
    -0.07
    おり
    -0.07
    rangle
    -0.07
     incentive
    -0.06
     у
    -0.06
     picnic
    -0.06
     older
    -0.06
    ňování
    -0.06
    Launching
    -0.06
    .sleep
    -0.06
    POSITIVE LOGITS
     dirs
    0.07
     здоб
    0.06
    getFullYear
    0.06
    woff
    0.06
     мають
    0.06
    	utils
    0.06
     �
    0.06
    егор
    0.06
     AutoMapper
    0.06
    bac
    0.06
    Act Density 0.004%

    No Known Activations