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

    Neuronpedia

    INDEX
    Explanations

    possessive 's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     CFP
    0.33
    Language
    0.30
     Zin
    0.30
    бні
    0.30
    Spread
    0.30
     SDN
    0.30
     최
    0.29
    최
    0.29
     Updated
    0.28
     unrealistic
    0.28
    POSITIVE LOGITS
     sacrifice
    0.36
     रेडियो
    0.34
     радио
    0.33
    anime
    0.33
     कर्म
    0.33
    anlage
    0.32
     festa
    0.32
     atriz
    0.31
     radi
    0.31
    }",
    0.31
    Act Density 0.068%

    No Known Activations