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

    Neuronpedia

    INDEX
    Explanations

    craft realistic dialogue

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    l
    0.80
    n
    0.78
    ncia
    0.75
     दिसंबर
    0.71
    mobility
    0.70
    lø
    0.70
    m
    0.70
    sk
    0.69
     kwiet
    0.68
     pagare
    0.68
    POSITIVE LOGITS
    CCOCC
    0.63
     Assay
    0.61
    هور
    0.60
     ggtitle
    0.60
     Supervis
    0.59
    ర్కొ
    0.59
     supervis
    0.58
    させる
    0.58
     Investig
    0.57
     quenching
    0.57
    Act Density 0.220%

    No Known Activations