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

    Neuronpedia

    INDEX
    Explanations

    chapters and descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🚺
    0.41
     réforme
    0.38
     kose
    0.38
    ♍
    0.38
    📽
    0.37
     playback
    0.37
    🦍
    0.36
     snelheid
    0.36
    🏟
    0.36
    👂
    0.36
    POSITIVE LOGITS
     Descriptions
    0.57
     descriptions
    0.54
     descriptive
    0.53
    Descriptions
    0.51
    descriptions
    0.51
     Descriptive
    0.51
     Chapter
    0.50
     Chapters
    0.50
    描述
    0.48
    Description
    0.46
    Act Density 0.000%

    No Known Activations