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

    Neuronpedia

    INDEX
    Explanations

    to bed

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     bedside
    0.45
     bedtime
    0.43
    сте
    0.39
     lull
    0.38
     inşa
    0.38
    䀒
    0.38
    इयों
    0.37
    改变
    0.36
    ͅ
    0.36
    🛌
    0.36
    POSITIVE LOGITS
    azion
    0.43
    Luego
    0.40
    ulk
    0.38
    XY
    0.38
     później
    0.38
     Hakim
    0.38
    ABCDEFGHIJKLMNOP
    0.37
     Di
    0.37
    Proud
    0.37
    î
    0.37
    Act Density 0.004%

    No Known Activations