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

    Neuronpedia

    INDEX
    Explanations

    jigsaw

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .kwargs
    -0.07
     Maybe
    -0.07
     fuzzy
    -0.07
     basis
    -0.07
    Floating
    -0.07
     lake
    -0.07
     expand
    -0.07
    樽
    -0.07
    Take
    -0.07
     Bay
    -0.07
    POSITIVE LOGITS
    thr
    0.08
    ])))
    0.08
    (coll
    0.07
    回到了
    0.07
    =$_
    0.07
    탭
    0.07
    .sh
    0.07
    네요
    0.07
    егодня
    0.07
    ELCOME
    0.07
    Act Density 0.016%

    No Known Activations