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

    Neuronpedia

    INDEX
    Explanations

    throughout

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _CLI
    -0.08
     convex
    -0.07
    _requested
    -0.07
    .tech
    -0.07
     predators
    -0.07
    wei
    -0.07
    变身
    -0.07
    _fwd
    -0.07
     *=
    -0.07
     Chi
    -0.07
    POSITIVE LOGITS
     throughout
    0.09
     ц
    0.07
    ﮪ
    0.07
     이것
    0.06
    作为
    0.06
     wag
    0.06
     escrit
    0.06
    ตรง
    0.06
     بالإض
    0.06
    จำ
    0.06
    Act Density 0.010%

    No Known Activations