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

    Neuronpedia

    INDEX
    Explanations

    &

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ’ll
    -0.08
    Ms
    -0.07
    ৺
    -0.07
    渝
    -0.07
     hath
    -0.07
    襄
    -0.07
    hs
    -0.07
     PAY
    -0.07
     enviar
    -0.06
     blowing
    -0.06
    POSITIVE LOGITS
    萝卜
    0.08
     accuse
    0.07
     strpos
    0.07
    ⁍
    0.07
     ?><?
    0.07
     })();↵
    0.07
    界限
    0.07
    (PyObject
    0.07
    系列产品
    0.06
    inded
    0.06
    Act Density 0.006%

    No Known Activations