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

    Neuronpedia

    INDEX
    Explanations

    specialkeywordsorparameters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ABILITIES
    0.45
    ប្រតិ
    0.45
    Reduce
    0.44
     मुझ
    0.42
    MTAB
    0.42
     variegated
    0.42
     washers
    0.41
    ayette
    0.41
     my
    0.41
     πυ
    0.41
    POSITIVE LOGITS
     있지만
    0.49
     chiffres
    0.48
    例えば
    0.47
    赛事
    0.45
     mesela
    0.45
     luoghi
    0.44
     milestone
    0.44
     estabele
    0.44
     mais
    0.44
     ولكن
    0.43
    Act Density 0.006%

    No Known Activations