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

    Neuronpedia

    INDEX
    Explanations

    after a or showed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tonight
    0.44
     emig
    0.43
     authorize
    0.42
     Guerra
    0.42
    .]
    0.42
    .
    0.41
    ネ
    0.41
     decree
    0.41
     ultimately
    0.40
     catalyze
    0.40
    POSITIVE LOGITS
    il
    0.45
    ach
    0.44
    xiety
    0.43
    aud
    0.43
    örm
    0.43
    üh
    0.42
    的说
    0.42
    ünschen
    0.42
    當中
    0.42
    atten
    0.41
    Act Density 0.008%

    No Known Activations