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

    Neuronpedia

    INDEX
    Explanations

    parameters and algorithms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    asons
    0.73
     lesser
    0.71
    ttle
    0.69
     serr
    0.65
    asas
    0.65
     particularly
    0.65
     pror
    0.65
     Sau
    0.65
     emailed
    0.64
     Dorn
    0.64
    POSITIVE LOGITS
    ๕
    0.89
    Š
    0.88
    effectuer
    0.88
    Algorithm
    0.88
    參數
    0.87
    Example
    0.85
    ಚಿತ
    0.84
     beş
    0.84
    Parameters
    0.84
     फाइव
    0.84
    Act Density 0.000%

    No Known Activations