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

    Neuronpedia

    INDEX
    Explanations

    political proposals

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bfs
    -0.07
     dump
    -0.07
    ieme
    -0.06
     Tap
    -0.06
    line
    -0.06
    apt
    -0.06
    Word
    -0.06
     cruiser
    -0.06
    规
    -0.06
     hann
    -0.06
    POSITIVE LOGITS
     restoring
    0.07
    CAL
    0.06
     cresc
    0.06
     Kendall
    0.06
    -www
    0.06
     gardening
    0.06
    θέ
    0.06
     aldığı
    0.06
    .CompareTo
    0.06
    íše
    0.06
    Act Density 0.045%

    No Known Activations