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
    Behaviour
    -0.07
    暴跌
    -0.07
     kw
    -0.07
    เฉ
    -0.07
    搽
    -0.06
     seperate
    -0.06
    env
    -0.06
     Seeds
    -0.06
    Centre
    -0.06
     signup
    -0.06
    POSITIVE LOGITS
     être
    0.07
     modeled
    0.07
    >').
    0.07
    ">'
    0.07
     collectors
    0.06
    _='
    0.06
    Ⲣ
    0.06
    ">',↵
    0.06
    	holder
    0.06
    רכים
    0.06
    Act Density 0.001%

    No Known Activations