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

    Neuronpedia

    INDEX
    Explanations

    policy outlines, travel arrangements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Indexer
    0.45
    IRT
    0.42
     unserer
    0.40
    odule
    0.39
     unim
    0.38
    Jurassic
    0.38
     ОО
    0.36
    lard
    0.36
     YAML
    0.36
    RED
    0.36
    POSITIVE LOGITS
    イッチ
    0.43
     이때
    0.40
    勁
    0.39
     grape
    0.39
    gaan
    0.39
     एक्सच
    0.37
     toks
    0.37
    ithin
    0.37
    電気
    0.36
    viamente
    0.36
    Act Density 0.002%

    No Known Activations