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

    Neuronpedia

    INDEX
    Explanations

    quantifiable, measurable, quantified

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    s
    0.58
    2
    0.57
    то
    0.42
     can
    0.42
    ra
    0.42
    还是要
    0.41
     pump
    0.41
    tr
    0.40
    total
    0.40
    USD
    0.40
    POSITIVE LOGITS
     utiles
    0.50
     biologists
    0.49
    DIRECTION
    0.48
     hilfreich
    0.47
     quantifiable
    0.47
    ้อย
    0.46
     measurable
    0.46
    ্ু
    0.45
    BinBuf
    0.45
     quantified
    0.44
    Act Density 0.002%

    No Known Activations