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

    Neuronpedia

    INDEX
    Explanations

    this course, this service, this topic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    0.45
     Př
    0.44
    Leather
    0.44
     Lip
    0.43
     Aircraft
    0.43
    <h2>
    0.43
    Getting
    0.43
     Ya
    0.43
     Getting
    0.42
     Kopf
    0.42
    POSITIVE LOGITS
     особенно
    0.45
    idee
    0.41
    ]=(
    0.39
     notably
    0.39
    कीपर
    0.38
    尤其是
    0.38
     आया
    0.37
     eyel
    0.37
    ={(
    0.37
     cycle
    0.36
    Act Density 0.001%

    No Known Activations