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

    Neuronpedia

    INDEX
    Explanations

    XML version declaration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     poisoning
    0.42
     primer
    0.39
     وده
    0.37
     poetry
    0.37
    orben
    0.36
     proportionately
    0.36
    curvature
    0.36
    ual
    0.36
     result
    0.35
     items
    0.35
    POSITIVE LOGITS
    版本
    0.46
    Version
    0.44
     版本
    0.43
    apagos
    0.41
    Какие
    0.41
     Version
    0.40
     Versions
    0.38
     версии
    0.38
     Tango
    0.37
     Kishan
    0.37
    Act Density 0.000%

    No Known Activations