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

    Neuronpedia

    INDEX
    Explanations

    .use

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     masses
    -0.06
    足
    -0.06
    =tk
    -0.06
    riere
    -0.06
    -г
    -0.06
    ophilia
    -0.06
     Haupt
    -0.06
     ArrayList
    -0.06
    ripe
    -0.06
     chall
    -0.06
    POSITIVE LOGITS
    .use
    0.10
    ")){
↵
    0.07
    ，所以
    0.06
     страш
    0.06
    *K
    0.06
     freezing
    0.06
     معرف
    0.06
    ypes
    0.06
     {\↵
    0.06
     развитие
    0.06
    Act Density 0.001%

    No Known Activations