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

    Neuronpedia

    INDEX
    Explanations

    data, power, model, education, dual

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ע
    0.50
    }}}
    0.48
    ก
    0.48
    ق
    0.46
    H
    0.45
    [
    0.42
    Emer
    0.42
    ગે
    0.42
    Q
    0.41
    //
    0.41
    POSITIVE LOGITS
     رجسٹریشن
    0.47
     denotes
    0.47
     rappresenta
    0.46
     registries
    0.46
     biasanya
    0.46
     tamper
    0.46
    naires
    0.44
     czyli
    0.44
     matrimon
    0.42
     generates
    0.42
    Act Density 0.001%

    No Known Activations