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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     selfish
    -0.07
     seinen
    -0.07
     ihren
    -0.07
     나타
    -0.06
     aqu
    -0.06
     LOCK
    -0.06
    _tax
    -0.06
    เฟ
    -0.06
    .Put
    -0.06
    显示
    -0.06
    POSITIVE LOGITS
    +-+-
    0.07
     delights
    0.07
     frau
    0.06
     Vikings
    0.06
    ercicio
    0.06
    essoa
    0.06
     MMI
    0.06
    众
    0.06
    科技
    0.06
    )*(
    0.06
    Act Density 0.192%

    No Known Activations