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

    Neuronpedia

    INDEX
    Explanations

    Moment Arm

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Kw
    0.48
     Biodiversity
    0.47
     Wor
    0.45
     adaptability
    0.44
    elin
    0.44
     Year
    0.43
     Adaptation
    0.43
     ఆలో
    0.43
     HashSet
    0.42
    ada
    0.42
    POSITIVE LOGITS
    રિક
    0.57
     fracking
    0.56
     láser
    0.56
    रा
    0.56
     latex
    0.55
     lá
    0.55
    تر
    0.54
    液
    0.54
    ଫ
    0.54
    یت
    0.53
    Act Density 0.000%

    No Known Activations