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

    Neuronpedia

    INDEX
    Explanations

    �

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    лара
    -0.08
    EDURE
    -0.08
    翔
    -0.07
    Chrome
    -0.07
     dungeon
    -0.07
    inst
    -0.07
    ौत
    -0.07
     Blizzard
    -0.07
     soma
    -0.07
    Drivers
    -0.07
    POSITIVE LOGITS
    _FE
    0.06
     �
    0.06
     additive
    0.06
    844
    0.06
    �
    0.06
    tığ
    0.06
     CAL
    0.06
     realization
    0.06
    emailer
    0.05
    ,args
    0.05
    Act Density 0.005%

    No Known Activations