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

    Neuronpedia

    INDEX
    Explanations

    slavery

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     edits
    -0.07
     js
    -0.07
    OPTIONS
    -0.07
     userName
    -0.07
     ej
    -0.06
    save
    -0.06
     Thesis
    -0.06
     zug
    -0.06
     Não
    -0.06
    speed
    -0.06
    POSITIVE LOGITS
    {}".
    0.07
    ندگان
    0.06
    DateFormat
    0.06
    .assertj
    0.06
    keeper
    0.06
    burse
    0.06
    貝
    0.06
    `]
    0.06
    (_)
    0.06
     Emerald
    0.06
    Act Density 0.023%

    No Known Activations