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

    Neuronpedia

    INDEX
    Explanations

    non-negotiable

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     மாநக
    0.72
    alloy
    0.66
    ায়ী
    0.65
    çay
    0.65
    ämän
    0.65
    ahuje
    0.65
    embourg
    0.63
    anyan
    0.63
    Project
    0.63
    Hop
    0.63
    POSITIVE LOGITS
     थ्री
    0.87
     inefficiencies
    0.85
     티
    0.85
     efficiencies
    0.83
     triv
    0.81
     ideales
    0.80
     Forks
    0.80
     repercussions
    0.79
    тивы
    0.79
    스티
    0.79
    Act Density 0.007%

    No Known Activations