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

    Neuronpedia

    INDEX
    Explanations

    core concepts or defining attributes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    en
    0.52
     dilihat
    0.48
    as
    0.47
    unciation
    0.47
    entukan
    0.46
    nung
    0.46
     dih
    0.46
    ệng
    0.46
    alakip
    0.46
    rrbracket
    0.45
    POSITIVE LOGITS
    SUMMARY
    0.49
    Moody
    0.46
    SampleSize
    0.45
     finances
    0.43
    Making
    0.42
    مث
    0.42
    Monkey
    0.42
    狮
    0.41
    精神
    0.41
    Ship
    0.41
    Act Density 0.000%

    No Known Activations