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

    Neuronpedia

    INDEX
    Explanations

    giving major

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    again
    0.89
    also
    0.82
    imen
    0.75
    Again
    0.71
    arsis
    0.71
    mdash
    0.70
    imetric
    0.69
    another
    0.67
    ütt
    0.67
    alsey
    0.67
    POSITIVE LOGITS
     vê
    0.74
     Firstly
    0.74
     tunique
    0.72
     Setting
    0.72
     რომელი
    0.70
     στον
    0.70
    <unused2204>
    0.69
    StudioProjects
    0.69
     legislação
    0.69
     Current
    0.69
    Act Density 0.582%

    No Known Activations