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

    Neuronpedia

    INDEX
    Explanations

    period

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ีบ
    -0.07
    之一
    -0.06
     Ж
    -0.06
    今
    -0.06
     deterministic
    -0.06
    -aged
    -0.06
    碼
    -0.06
     Dice
    -0.06
     experimentation
    -0.06
     Contemporary
    -0.06
    POSITIVE LOGITS
    ="../../../
    0.07
     verilm
    0.06
    .ogg
    0.06
     tul
    0.06
    areas
    0.06
     Someone
    0.06
     squeez
    0.06
     tok
    0.06
     steals
    0.06
     renting
    0.06
    Act Density 0.002%

    No Known Activations