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

    Neuronpedia

    INDEX
    Explanations

    reply

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     positrons
    0.39
     oscillators
    0.37
     cesium
    0.36
     homot
    0.36
    মাতে
    0.36
    ThemeOverlay
    0.35
    ^{*}$
    0.35
    eningkatan
    0.35
    蝗
    0.35
    inergic
    0.34
    POSITIVE LOGITS
     reply
    3.13
     Reply
    2.86
     replying
    2.86
     replies
    2.81
    reply
    2.77
     replied
    2.75
    Reply
    2.75
     REPLY
    2.63
     Replies
    2.34
    回复
    2.27
    Act Density 0.022%

    No Known Activations