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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    BIG
    -0.07
     tweeted
    -0.06
     activated
    -0.06
     yüksek
    -0.06
    Arduino
    -0.06
    nesty
    -0.06
     Bez
    -0.05
    システム
    -0.05
    oded
    -0.05
    Study
    -0.05
    POSITIVE LOGITS
    .draw
    0.07
     تاب
    0.07
     inflatable
    0.07
    tener
    0.07
    <label
    0.07
     Mare
    0.06
     محمود
    0.06
     Tucker
    0.06
    ;left
    0.06
    ense
    0.06
    Act Density 0.071%

    No Known Activations