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

    Neuronpedia

    INDEX
    Explanations

    grinding, dance, static

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Caching
    0.55
    ,-
    0.53
    containsKey
    0.51
     habis
    0.51
     Mode
    0.49
     Constitu
    0.49
     Mist
    0.48
    ือด
    0.48
     Assam
    0.47
     Comité
    0.47
    POSITIVE LOGITS
     nějak
    0.47
    the
    0.46
     gör
    0.45
     серед
    0.45
     imao
    0.45
     доба
    0.44
     gotten
    0.44
     اند
    0.44
    iformis
    0.44
     střed
    0.44
    Act Density 0.000%

    No Known Activations