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

    Neuronpedia

    INDEX
    Explanations

    everyone, everything, all

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    م
    0.60
     muqueuse
    0.60
    แดง
    0.53
     startling
    0.53
    轅
    0.53
    पर
    0.52
    ør
    0.52
    ренные
    0.52
     wrongfully
    0.52
    س
    0.51
    POSITIVE LOGITS
    ergic
    0.76
    iances
    0.73
    iteration
    0.71
    igators
    0.66
    iterate
    0.63
    recipes
    0.63
     sorts
    0.62
    ل
    0.61
    aying
    0.61
     demás
    0.61
    Act Density 0.150%

    No Known Activations