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

    Neuronpedia

    INDEX
    Explanations

    possessive 's' or abbreviations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     obfusc
    0.34
     ingrained
    0.31
     materi
    0.31
     metaphor
    0.31
     manipul
    0.31
    ,
    0.30
     nebul
    0.30
     nerd
    0.29
     damp
    0.29
     얼마나
    0.29
    POSITIVE LOGITS
    Cm
    0.42
    Currency
    0.41
    Sharma
    0.39
    RationalValue
    0.39
    Eve
    0.39
    Ltd
    0.38
    <unused1775>
    0.38
    Adm
    0.38
    <unused2006>
    0.38
    Ahora
    0.38
    Act Density 6.237%

    No Known Activations