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

    Neuronpedia

    INDEX
    Explanations

    3

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Tb
    -0.07
     Boss
    -0.07
     Temper
    -0.06
    gres
    -0.06
     reliable
    -0.06
    sonian
    -0.06
     bf
    -0.06
     Faul
    -0.06
    Db
    -0.06
    flip
    -0.06
    POSITIVE LOGITS
    );?>↵
    0.06
    はない
    0.06
    цией
    0.06
     %{
    0.06
    ряд
    0.06
     �
    0.06
    .keyword
    0.06
    處
    0.06
     adresse
    0.06
     CLOCK
    0.06
    Act Density 0.002%

    No Known Activations