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

    Neuronpedia

    INDEX
    Explanations

    software releases

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ken
    -0.07
     önc
    -0.06
     PIPE
    -0.06
    Fragment
    -0.06
    โจ
    -0.06
    KEN
    -0.06
     Hàng
    -0.06
    Child
    -0.06
     Obama
    -0.06
     ráp
    -0.06
    POSITIVE LOGITS
     dív
    0.07
    .Publish
    0.06
    ETHOD
    0.06
    .measure
    0.06
    iphers
    0.06
     світ
    0.06
     leftover
    0.06
     altercation
    0.06
     hak
    0.06
    .putInt
    0.06
    Act Density 0.043%

    No Known Activations