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

    Neuronpedia

    INDEX
    Explanations

    button states

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     llama
    -0.07
     draggable
    -0.06
     irrigation
    -0.06
    ınd
    -0.06
    oru
    -0.06
    ωμάτιο
    -0.06
     floppy
    -0.06
     Hiệp
    -0.06
     letto
    -0.06
     intervene
    -0.06
    POSITIVE LOGITS
    澤
    0.07
    /respond
    0.06
     correctness
    0.06
    .random
    0.06
     overhaul
    0.06
     comp
    0.06
     Spotify
    0.06
    (site
    0.06
    .setHorizontal
    0.06
     zoom
    0.06
    Act Density 0.021%

    No Known Activations