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

    Neuronpedia

    INDEX
    Explanations

    say ")"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sewing
    -0.07
    505
    -0.07
     Warp
    -0.07
    选择
    -0.07
    Machine
    -0.07
    шими
    -0.06
    /uploads
    -0.06
    typedef
    -0.06
    primitive
    -0.06
    NIEnv
    -0.06
    POSITIVE LOGITS
    leck
    0.06
    นค
    0.06
    �
    0.06
    orgt
    0.06
     Platz
    0.06
     jes
    0.06
    lemen
    0.06
     inversion
    0.06
    _J
    0.06
     Př
    0.06
    Act Density 0.005%

    No Known Activations