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

    Neuronpedia

    INDEX
    Explanations

    drafting text or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    proj
    0.51
    gz
    0.47
    gli
    0.47
    âge
    0.46
    ALY
    0.46
     archi
    0.46
    ALL
    0.45
     contribu
    0.45
    Kt
    0.45
    ͊
    0.45
    POSITIVE LOGITS
     Newtonsoft
    0.45
     owing
    0.45
    中
    0.43
     /
    0.42
     Shrimp
    0.42
     "-
    0.40
     +"\
    0.40
    익
    0.40
    车型
    0.40
     Owing
    0.40
    Act Density 0.000%

    No Known Activations