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

    Neuronpedia

    INDEX
    Explanations

    Intervention or program

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Frames
    -0.07
     Debian
    -0.07
    Dto
    -0.07
    ीस
    -0.06
    좋
    -0.06
    -image
    -0.06
     Rahul
    -0.06
     funnel
    -0.06
    微笑
    -0.06
     hafta
    -0.06
    POSITIVE LOGITS
     läng
    0.07
     mult
    0.07
     ability
    0.06
    abyrin
    0.06
     Elegant
    0.06
     Rest
    0.06
     قسمت
    0.06
    visual
    0.06
    Meter
    0.06
     ikt
    0.06
    Act Density 0.021%

    No Known Activations