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

    Neuronpedia

    INDEX
    Explanations

    official document headers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     selfies
    1.02
     puzzles
    0.88
     tang
    0.87
     physicality
    0.86
     realistically
    0.85
     배워
    0.84
     movies
    0.84
     realistic
    0.83
     lasagna
    0.82
    どんな
    0.81
    POSITIVE LOGITS
     memorandum
    1.57
     Memorandum
    1.54
     issued
    1.48
     dated
    1.46
    Memor
    1.42
     Circular
    1.37
     Issued
    1.36
     Amendment
    1.34
    issued
    1.34
     document
    1.31
    Act Density 0.189%

    No Known Activations