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

    Neuronpedia

    INDEX
    Explanations

    Version control

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -general
    -0.07
     }):
    -0.07
     demographics
    -0.07
    હ
    -0.07
    心理
    -0.07
    هل
    -0.07
    ENV
    -0.07
    coords
    -0.07
     mutate
    -0.07
     geopol
    -0.07
    POSITIVE LOGITS
     nächsten
    0.07
    两人
    0.07
     invasion
    0.07
     Griff
    0.07
    ⵎ
    0.07
    替代
    0.06
     Trie
    0.06
     Years
    0.06
     limit
    0.06
    WM
    0.06
    Act Density 0.001%

    No Known Activations