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

    Neuronpedia

    INDEX
    Explanations

    technical explanations and queries

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ur
    0.54
    يد
    0.49
    לו
    0.49
    కి
    0.46
    us
    0.45
    ig
    0.45
    ans
    0.45
    adur
    0.45
    ᓱ
    0.44
     Behaviour
    0.43
    POSITIVE LOGITS
     cylinder
    0.55
     methane
    0.55
     six
    0.46
     steering
    0.46
     vale
    0.46
     方法
    0.46
     hexagonal
    0.45
     nele
    0.45
     negotiating
    0.45
     شورای
    0.45
    Act Density 0.001%

    No Known Activations