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

    Neuronpedia

    INDEX
    Explanations

    gradual change and transitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    1
    0.62
    ated
    0.61
    ene
    0.59
    icking
    0.58
    aks
    0.55
    age
    0.55
    انی
    0.55
    ancers
    0.55
    acks
    0.54
    acha
    0.54
    POSITIVE LOGITS
    ل
    0.66
     gradually
    0.63
    ر
    0.61
    بيه
    0.59
    ো
    0.59
     dần
    0.57
    o
    0.55
     Goodyear
    0.54
    越来越多
    0.54
    نتي
    0.53
    Act Density 0.305%

    No Known Activations