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

    Neuronpedia

    INDEX
    Explanations

    "a" or "A" followed by common words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ⴻ
    0.41
    េទ
    0.40
    밂
    0.40
    Peq
    0.39
    电商
    0.39
    昷
    0.38
    ﮢ
    0.37
    ointers
    0.37
    echolog
    0.37
    剛剛
    0.37
    POSITIVE LOGITS
     church
    0.43
     four
    0.39
     three
    0.38
     promise
    0.38
     long
    0.38
     back
    0.38
     mass
    0.38
     two
    0.37
    0.37
     daughter
    0.36
    Act Density 0.000%

    No Known Activations