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

    Neuronpedia

    INDEX
    Explanations

    maintain or facilitate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     political
    0.47
    grat
    0.45
    你应该
    0.45
    说
    0.44
    political
    0.44
     सारी
    0.44
    Carol
    0.44
    es
    0.43
    spolit
    0.43
    ह
    0.43
    POSITIVE LOGITS
     край
    0.52
     ミニ
    0.48
     obey
    0.44
     textArea
    0.44
     стандарт
    0.44
    0.44
     graphically
    0.43
    ភេទ
    0.43
    ゾーン
    0.43
     न्यूनतम
    0.42
    Act Density 0.003%

    No Known Activations