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

    Neuronpedia

    INDEX
    Explanations

    Unified

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _course
    -0.07
    ＝
    -0.07
    птом
    -0.06
     Chance
    -0.06
    rooms
    -0.06
     �
    -0.06
    IGHL
    -0.06
     دشمن
    -0.06
    цять
    -0.06
    卻
    -0.06
    POSITIVE LOGITS
     unified
    0.14
     Unified
    0.13
     unify
    0.10
    Unified
    0.09
     통합
    0.08
    統
    0.07
     updated
    0.07
     homicides
    0.07
     RequestMethod
    0.07
     Hogwarts
    0.07
    Act Density 0.002%

    No Known Activations