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

    Neuronpedia

    INDEX
    Explanations

    place names

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Uploader
    -0.07
    	REG
    -0.07
    sik
    -0.07
     WEB
    -0.06
     Buffett
    -0.06
    ä
    -0.06
    CAN
    -0.06
    ized
    -0.06
     сем
    -0.06
     outraged
    -0.06
    POSITIVE LOGITS
    aries
    0.07
    �
    0.07
    jl
    0.07
    choose
    0.07
     Collaboration
    0.06
     knobs
    0.06
    弹
    0.06
    恨
    0.06
     hide
    0.06
    _ENSURE
    0.06
    Act Density 0.000%

    No Known Activations