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

    Neuronpedia

    INDEX
    Explanations

    decision variables or inputs

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pairing
    0.47
    odoxy
    0.46
    CEEDINGS
    0.42
    विच
    0.40
    udahkan
    0.40
     Phang
    0.40
     comparing
    0.40
    ندگان
    0.40
     pairing
    0.39
     sticking
    0.39
    POSITIVE LOGITS
    更是
    0.38
     Entom
    0.38
     Either
    0.36
     Ше
    0.36
    Carroll
    0.35
     Carroll
    0.35
     lifestyles
    0.35
    sizes
    0.35
    𝚖
    0.35
     rag
    0.34
    Act Density 0.001%

    No Known Activations