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

    Neuronpedia

    INDEX
    Explanations

    information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    вед
    -0.07
     vực
    -0.06
     God
    -0.06
     resta
    -0.06
    addons
    -0.06
    cheon
    -0.06
    balls
    -0.06
     Fif
    -0.06
    ])+
    -0.06
    -x
    -0.06
    POSITIVE LOGITS
     Twin
    0.07
    하였다
    0.06
    eterminate
    0.06
    _pref
    0.06
     κό
    0.06
    -op
    0.06
    ******↵
    0.06
    gli
    0.06
     unsure
    0.06
     cooperation
    0.06
    Act Density 0.038%

    No Known Activations