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

    Neuronpedia

    INDEX
    Explanations

    mix of languages and scripts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াল
    2.02
    рный
    1.78
     convection
    1.76
    yllic
    1.75
    ǘ
    1.74
    roasted
    1.73
     stunted
    1.73
    islation
    1.70
    1.70
    ਰ
    1.69
    POSITIVE LOGITS
    nya
    1.71
    وں
    1.62
    产权
    1.57
    és
    1.54
    ness
    1.49
    to
    1.44
    set
    1.42
    dns
    1.42
     débit
    1.41
    이면
    1.40
    Act Density 0.000%

    No Known Activations