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

    Neuronpedia

    INDEX
    Explanations

    Math symbols

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ToEnd
    -0.07
    ucson
    -0.07
     Lexington
    -0.07
    estr
    -0.06
    ondon
    -0.06
     сл
    -0.06
     أنا
    -0.06
     дв
    -0.06
     dever
    -0.06
    DITION
    -0.06
    POSITIVE LOGITS
    startTime
    0.07
    ")↵
    0.06
     �
    0.06
    &#
    0.06
     STDMETHODCALLTYPE
    0.06
     batching
    0.06
    ()-
    0.06
     bypass
    0.06
    매
    0.06
     Hilfe
    0.06
    Act Density 0.035%

    No Known Activations