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

    Neuronpedia

    INDEX
    Explanations

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tk
    -0.07
    anske
    -0.07
     fortified
    -0.06
     ));
↵
    -0.06
    ’a
    -0.06
    Everyone
    -0.06
    ่อ
    -0.06
     bunk
    -0.06
    .Bl
    -0.06
     UDP
    -0.06
    POSITIVE LOGITS
    만원입니다
    0.07
     Carpet
    0.06
    about
    0.06
     wrappers
    0.06
    approximately
    0.06
    illaume
    0.06
    both
    0.06
    matches
    0.06
    Sweet
    0.06
     cerr
    0.06
    Act Density 0.253%

    No Known Activations