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

    Neuronpedia

    INDEX
    Explanations

    **Names** and titles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Mes
    0.50
     Crist
    0.44
    خ
    0.43
    𝘣
    0.43
     Go
    0.42
     Hoch
    0.42
     tient
    0.41
    動画
    0.41
     vois
    0.41
    Ро
    0.41
    POSITIVE LOGITS
     ಆದ
    0.46
     waisted
    0.46
     slowed
    0.46
     ಸಂಧಿ
    0.46
     hoisted
    0.45
     stronghold
    0.44
     cooled
    0.44
     substantiated
    0.44
     darkened
    0.44
     darkening
    0.43
    Act Density 0.001%

    No Known Activations