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

    Neuronpedia

    INDEX
    Explanations

    citing sources

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     프랑스
    -0.07
    archy
    -0.07
     Emerald
    -0.07
     права
    -0.07
     evolving
    -0.07
    inese
    -0.07
    co
    -0.06
    ในป
    -0.06
     Prefer
    -0.06
    encia
    -0.06
    POSITIVE LOGITS
    VMLINUX
    0.07
    Did
    0.07
     tane
    0.06
    ycz
    0.06
    457
    0.06
     />,
    0.06
    mour
    0.06
    _Is
    0.06
     Initialise
    0.06
    463
    0.06
    Act Density 0.040%

    No Known Activations