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

    Neuronpedia

    INDEX
    Explanations

    configuration and strategy

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Pedra
    0.43
    жается
    0.40
    Grove
    0.36
    TRUST
    0.35
     dessas
    0.35
    жна
    0.34
    いましたが
    0.34
    ");*/
    0.34
    দর
    0.34
     Silvia
    0.34
    POSITIVE LOGITS
     Utilization
    0.39
     maximise
    0.38
     prefix
    0.38
     utilization
    0.37
     correction
    0.35
     maximize
    0.35
     využ
    0.35
     adjustable
    0.34
     logarithm
    0.34
    adjustable
    0.34
    Act Density 0.000%

    No Known Activations