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

    Neuronpedia

    INDEX
    Explanations

    muscle tense and release

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     relev
    1.24
    러스
    1.11
     marav
    1.08
     Nope
    1.07
     encirc
    1.07
    TING
    1.05
     Unterricht
    1.04
     verbunden
    1.02
     edición
    1.02
     CHAIN
    1.01
    POSITIVE LOGITS
    ক্ষেত্রে
    1.11
    ensitive
    1.11
    blatt
    1.07
     इसे
    1.05
    ス
    1.05
    etsu
    1.03
    yaml
    1.03
    necked
    1.01
    t
    1.01
     Kumari
    1.00
    Act Density 0.001%

    No Known Activations