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

    Neuronpedia

    INDEX
    Explanations

    film reviews

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Friday
    -0.07
     Olsen
    -0.07
    alance
    -0.07
     disproportionately
    -0.07
    rhs
    -0.06
    	change
    -0.06
    ์ว
    -0.06
     nichts
    -0.06
     harming
    -0.06
    ž
    -0.06
    POSITIVE LOGITS
    idlo
    0.06
    προ
    0.06
     Parcel
    0.06
    icester
    0.06
    τέλε
    0.06
     المت
    0.06
    рак
    0.06
     ชนะ
    0.06
    DBus
    0.06
     ưu
    0.06
    Act Density 0.083%

    No Known Activations