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

    Neuronpedia

    INDEX
    Explanations

    that followed by specific words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    add
    0.42
    ደት
    0.40
    ބ
    0.39
    Pagination
    0.39
    صد
    0.38
     UTF
    0.37
    这么多
    0.37
    آ
    0.37
    ጽ
    0.37
     ధ
    0.37
    POSITIVE LOGITS
    iren
    0.41
     RL
    0.40
     underlie
    0.38
    ires
    0.37
    ieras
    0.36
     Alic
    0.36
     College
    0.36
     antique
    0.36
    ier
    0.36
     pose
    0.35
    Act Density 0.006%

    No Known Activations