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

    Neuronpedia

    INDEX
    Explanations

    ask

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .placeholder
    -0.08
     Twe
    -0.07
    -Aug
    -0.07
    cripting
    -0.07
     kannattaa
    -0.07
     gains
    -0.07
     ഉണ്ടായ
    -0.07
    feeds
    -0.07
     tendencies
    -0.07
     sejumlah
    -0.07
    POSITIVE LOGITS
     justamente
    0.10
    的是
    0.09
     verlangt
    0.08
     Perc
    0.08
    (click
    0.08
     منك
    0.08
    ว่า
    0.08
    Perc
    0.08
    Answered
    0.08
     ambiguous
    0.07
    Act Density 0.028%

    No Known Activations