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

    Neuronpedia

    INDEX
    Explanations

    save the code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     activating
    0.85
     trays
    0.69
     행사
    0.67
     activation
    0.67
     sporadically
    0.66
     путеше
    0.65
     turnt
    0.65
     sneaking
    0.64
    わざ
    0.64
     ప్రయత్
    0.64
    POSITIVE LOGITS
     contents
    1.07
    contents
    1.04
     내용은
    1.02
    Contents
    1.00
     내용을
    0.98
     保存
    0.97
    保存
    0.97
     Contents
    0.96
     contenu
    0.92
    上記
    0.91
    Act Density 0.035%

    No Known Activations