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

    Neuronpedia

    INDEX
    Explanations

    prefix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (year
    -0.07
    "fmt
    -0.07
    istream
    -0.06
    izzes
    -0.06
     Brew
    -0.06
    	Vector
    -0.06
     slowly
    -0.06
    umber
    -0.06
    靈
    -0.06
    270
    -0.06
    POSITIVE LOGITS
    做
    0.07
     tt
    0.06
     =========================================================================
    0.06
    Ignoring
    0.06
    ipherals
    0.06
    訴
    0.06
     Ao
    0.06
     EFFECT
    0.06
    SP
    0.06
     Scr
    0.06
    Act Density 0.004%

    No Known Activations