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

    Neuronpedia

    INDEX
    Explanations

    quiet descriptive qualities

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     }{}_{\
    0.57
     TouchUtils
    0.53
     Unable
    0.50
     problémy
    0.48
    '];
    0.47
    </th>
    0.47
     !_
    0.46
    </h5>
    0.45
    』（
    0.45
     PROBLEMS
    0.44
    POSITIVE LOGITS
    in
    0.60
    ご
    0.56
    at
    0.54
    gehend
    0.52
    落ち着
    0.52
    ام
    0.52
    rard
    0.51
    心里
    0.50
    ່ວ
    0.50
     leisurely
    0.50
    Act Density 0.008%

    No Known Activations