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

    Neuronpedia

    INDEX
    Explanations

    Possessives and conjunctions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     divine
    0.40
     bundan
    0.40
    टि
    0.38
    onymous
    0.37
     വാ
    0.36
    );*/
    0.36
     насеље
    0.36
    izion
    0.36
     там
    0.36
    accio
    0.36
    POSITIVE LOGITS
     its
    0.51
    及其
    0.50
     Its
    0.40
     alrededores
    0.39
     اطراف
    0.38
    使其
    0.38
    看似
    0.37
    它的
    0.37
    Its
    0.36
     INCLUDING
    0.36
    Act Density 0.068%

    No Known Activations