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

    Neuronpedia

    INDEX
    Explanations

    n <= guard

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     pom
    0.45
     POM
    0.39
    POM
    0.39
    Pom
    0.38
     Examin
    0.35
    ellingen
    0.34
    如果你
    0.34
     lắng
    0.34
     ادار
    0.34
     Pom
    0.33
    POSITIVE LOGITS
    dumb
    0.40
    三
    0.38
     Dumb
    0.37
     Caucasian
    0.37
    este
    0.36
     -=
    0.36
     psychosis
    0.35
    spacerItem
    0.35
    |=|
    0.35
     dumb
    0.35
    Act Density 0.005%

    No Known Activations