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

    Neuronpedia

    INDEX
    Explanations

    emails

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Entertainment
    -0.07
     exposure
    -0.07
     Ryder
    -0.07
    커스
    -0.07
    ablish
    -0.07
    ACHI
    -0.06
     opening
    -0.06
     asks
    -0.06
     narrow
    -0.06
     LE
    -0.06
    POSITIVE LOGITS
    numberOf
    0.07
     NSStringFromClass
    0.07
    (retval
    0.07
     obtains
    0.07
    466
    0.07
    魚
    0.07
    ']."
    0.07
     عکس
    0.07
    tres
    0.07
    WithName
    0.06
    Act Density 0.015%

    No Known Activations