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

    Neuronpedia

    INDEX
    Explanations

    information; need for access

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     SH
    0.79
    NG
    0.78
    MEN
    0.76
     Hotels
    0.75
    SH
    0.75
     Boiler
    0.74
     HO
    0.74
    Squares
    0.73
    cms
    0.73
    ਪ
    0.73
    POSITIVE LOGITS
    具体
    0.82
     paucity
    0.74
    такт
    0.73
     obtenus
    0.73
     dẫn
    0.73
    确保
    0.73
     positifs
    0.72
    对于
    0.71
     εί
    0.71
     gehört
    0.71
    Act Density 0.000%

    No Known Activations