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

    Neuronpedia

    INDEX
    Explanations

    text or code context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Protein
    0.38
     METHOD
    0.38
     Orta
    0.38
     мисте
    0.37
     яи
    0.37
     మహి
    0.36
    нцип
    0.36
    antam
    0.36
    等级
    0.36
    тельской
    0.36
    POSITIVE LOGITS
     puff
    0.42
    េរ
    0.40
    Dest
    0.38
    Parents
    0.38
    uban
    0.38
    LP
    0.37
     residence
    0.37
     impart
    0.37
    Sz
    0.37
    ទទ
    0.37
    Act Density 0.001%

    No Known Activations