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

    Neuronpedia

    INDEX
    Explanations

    class, because other methods failed

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    buz
    -0.07
     dwelling
    -0.07
    wealth
    -0.06
    Increasing
    -0.06
    School
    -0.06
    گیرد
    -0.06
     cond
    -0.06
     bureauc
    -0.06
     และ
    -0.06
    uvo
    -0.06
    POSITIVE LOGITS
    (sid
    0.07
    .FromSeconds
    0.06
     Abb
    0.06
    産
    0.06
    _BYTE
    0.06
     Johann
    0.06
    Spawn
    0.06
     onOptionsItemSelected
    0.06
    %%
    0.06
    _exempt
    0.06
    Act Density 0.152%

    No Known Activations