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

    Neuronpedia

    INDEX
    Explanations

    $

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ức
    -0.07
     dic
    -0.07
    (OP
    -0.07
     Ricky
    -0.07
    (comm
    -0.07
     bere
    -0.06
     Nick
    -0.06
     dest
    -0.06
     bitterly
    -0.06
     lắng
    -0.06
    POSITIVE LOGITS
     무
    0.07
    扽
    0.07
    liquid
    0.06
    妇科
    0.06
    �
    0.06
    Ⲟ
    0.06
    几乎是
    0.06
    ?a
    0.06
    }\\
    0.06
    פוט
    0.06
    Act Density 0.027%

    No Known Activations