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

    Neuronpedia

    INDEX
    Explanations

    pre-trained and pre-built

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    causing
    0.85
    께
    0.75
    仍在
    0.70
    inducing
    0.69
    ではない
    0.69
    induced
    0.69
     нрави
    0.68
    τζ
    0.68
     causing
    0.68
    da
    0.67
    POSITIVE LOGITS
     trip
    0.86
     ಮಾಡಿದ
    0.76
     dibuat
    0.75
     repentance
    0.75
     programu
    0.72
     stroke
    0.72
     configur
    0.72
     victory
    0.72
     stok
    0.70
     existence
    0.70
    Act Density 0.031%

    No Known Activations