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

    Neuronpedia

    INDEX
    Explanations

    payments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .strftime
    -0.07
    存在
    -0.07
    供
    -0.07
     hombre
    -0.07
     Significant
    -0.06
     Israelis
    -0.06
     defiant
    -0.06
     fruits
    -0.06
     जय
    -0.06
    urous
    -0.06
    POSITIVE LOGITS
    DEV
    0.07
    =headers
    0.06
     переп
    0.06
    political
    0.06
    -static
    0.06
    Depending
    0.06
     Fl
    0.06
    pled
    0.06
     faux
    0.06
    	Long
    0.06
    Act Density 0.083%

    No Known Activations