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

    Neuronpedia

    INDEX
    Explanations

    instructions, examples, or conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     few
    0.39
     Few
    0.38
     Celebrating
    0.38
     Beware
    0.38
    的一些
    0.37
     Successfully
    0.37
     Can
    0.37
     Differences
    0.37
     George
    0.36
     Some
    0.36
    POSITIVE LOGITS
    ګ
    0.47
    ಮಾನ
    0.42
    abies
    0.39
     refugee
    0.38
    lasses
    0.38
    ګه
    0.38
     bureaucracy
    0.37
    Gruppe
    0.37
    Plist
    0.37
    FERENCE
    0.37
    Act Density 0.008%

    No Known Activations