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

    Neuronpedia

    INDEX
    Explanations

    Question words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .message
    -0.07
    ніцип
    -0.07
    ilim
    -0.06
     Cop
    -0.06
     createUser
    -0.06
     Luigi
    -0.06
     buried
    -0.06
     aggregates
    -0.06
     yaptığ
    -0.06
    اني
    -0.06
    POSITIVE LOGITS
     어떤
    0.13
    [^
    0.07
    __↵↵
    0.07
     어떻게
    0.07
    、どう
    0.07
    、何
    0.07
    ่าการ
    0.07
    _REFERENCE
    0.06
     )"
    0.06
     nasıl
    0.06
    Act Density 0.006%

    No Known Activations