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

    Neuronpedia

    INDEX
    Explanations

    identity

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     dispens
    -0.07
    -0.07
     dehydration
    -0.07
    -0.07
     recordings
    -0.07
     plateau
    -0.07
    tty
    -0.07
     Ru
    -0.07
    .interceptor
    -0.07
     stopwatch
    -0.07
    POSITIVE LOGITS
     américaine
    0.09
     américain
    0.08
     horribly
    0.08
     kê
    0.08
     américains
    0.08
     वित्त
    0.08
     nort
    0.08
    �
    0.08
     अमेरिक
    0.08
    严重
    0.08
    Act Density 0.007%
    No Known Activations