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

    Neuronpedia

    INDEX
    Explanations

    not

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     telesc
    -0.08
    _energy
    -0.07
    .trigger
    -0.07
    าตรฐาน
    -0.07
    +=(
    -0.06
     misd
    -0.06
     toxic
    -0.06
    ----
    -0.06
    .freeze
    -0.06
    =
    -0.06
    POSITIVE LOGITS
     Počet
    0.07
    也不
    0.07
    ンブ
    0.07
     Lawyers
    0.06
     UNSIGNED
    0.06
    ีความ
    0.06
    .lot
    0.06
    不
    0.06
     �
    0.06
     dlou
    0.06
    Act Density 0.026%

    No Known Activations