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

    Neuronpedia

    INDEX
    Explanations

    foreign language words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    sa
    0.55
    ousing
    0.49
    yn
    0.46
     chemist
    0.46
    size
    0.44
     burdened
    0.44
     Zusch
    0.43
    itating
    0.43
    "]:
    0.43
     charred
    0.43
    POSITIVE LOGITS
    Dedicated
    0.49
    Guitar
    0.48
    Exact
    0.47
     étoile
    0.47
    คู่
    0.47
     представления
    0.46
    बाह
    0.45
     //}
    0.45
    FAC
    0.45
    蜃
    0.45
    Act Density 0.111%

    No Known Activations