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

    Neuronpedia

    INDEX
    Explanations

    glowing orb or sphere

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    commitment
    0.53
    rit
    0.50
    cerr
    0.49
    variety
    0.48
    両
    0.46
    ouncement
    0.45
    ুল
    0.44
    νη
    0.44
    idia
    0.44
     Tags
    0.44
    POSITIVE LOGITS
     Thoreau
    0.47
    эс
    0.45
     indestructible
    0.44
     मेरा
    0.44
     أب
    0.44
     öner
    0.44
     ejected
    0.43
     большой
    0.43
     lässt
    0.42
    здат
    0.42
    Act Density 0.001%

    No Known Activations