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

    Neuronpedia

    INDEX
    Explanations

    formal writing

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     departed
    -0.08
    _loc
    -0.07
    _Show
    -0.06
     木
    -0.06
     Це
    -0.06
     operate
    -0.06
    Chess
    -0.06
     تصو
    -0.06
     interacts
    -0.06
    Combined
    -0.06
    POSITIVE LOGITS
     Crist
    0.07
    いや
    0.07
     Loved
    0.07
     RPG
    0.06
    kup
    0.06
     Jur
    0.06
    /event
    0.06
     SMALL
    0.06
     pemb
    0.06
     cleric
    0.06
    Act Density 0.000%

    No Known Activations