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

    Neuronpedia

    INDEX
    Explanations

    numbers and units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     понятно
    0.47
    다면
    0.46
    别人的
    0.45
     hashedPassword
    0.45
     گلوکار
    0.44
     생각해
    0.44
    孩子
    0.44
    ั้ย
    0.44
     जस्टिस
    0.43
     বিষয়
    0.41
    POSITIVE LOGITS
    0
    0.98
     miljoen
    0.70
    ０
    0.66
     acres
    0.65
     litre
    0.64
    kHz
    0.64
     hectare
    0.64
    5
    0.64
     hectares
    0.63
     jähr
    0.63
    Act Density 0.001%

    No Known Activations