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

    Neuronpedia

    INDEX
    Explanations

    automatic update checking

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Modeling
    0.47
     Modeling
    0.42
    modeling
    0.41
    Preprocessing
    0.41
     modeling
    0.41
     conversions
    0.41
    Mental
    0.40
    Interpret
    0.40
     Modelling
    0.39
    “,
    0.39
    POSITIVE LOGITS
     checkFor
    0.78
    checkFor
    0.77
     updater
    0.74
     update
    0.68
    Updater
    0.68
     Updater
    0.68
     checker
    0.67
     Update
    0.65
    检查
    0.64
     check
    0.64
    Act Density 0.028%

    No Known Activations