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

    Neuronpedia

    INDEX
    Explanations

    defining explanations and cases

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ड्र
    0.47
     سلا
    0.44
    arcz
    0.41
     Quận
    0.41
    versi
    0.41
    oyed
    0.40
     నిజ
    0.40
     කැ
    0.39
    ស្ល
    0.39
    اره
    0.38
    POSITIVE LOGITS
     an
    0.46
    Heather
    0.44
     Heather
    0.38
     espress
    0.38
     interpre
    0.37
     impulsive
    0.37
    Sophie
    0.36
    !<
    0.36
     rund
    0.36
     interpretations
    0.36
    Act Density 0.001%

    No Known Activations