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

    Neuronpedia

    INDEX
    Explanations

    quantifier + noun/state

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     অথবা
    0.45
    √
    0.40
    Convert
    0.39
     अनलिमिटेड
    0.38
    随时
    0.38
     convert
    0.38
    ላ
    0.38
    Roots
    0.37
    Arth
    0.37
    Strateg
    0.37
    POSITIVE LOGITS
     pris
    0.38
    铣
    0.38
     Teacher
    0.38
     Seminar
    0.38
     Another
    0.38
    ParentElement
    0.37
     joka
    0.37
     másik
    0.37
     pelaksanaan
    0.36
     হইতেছিল
    0.36
    Act Density 0.004%

    No Known Activations