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

    Neuronpedia

    INDEX
    Explanations

    costs and categories

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝚎
    0.52
     SEE
    0.50
     SELL
    0.49
    wala
    0.49
     Chopra
    0.46
     arma
    0.45
     HOURS
    0.45
     Beschreibung
    0.44
     hoofdst
    0.44
    𝟘
    0.44
    POSITIVE LOGITS
    Pilot
    0.41
    inic
    0.40
    Sources
    0.39
    菟
    0.39
    Masters
    0.39
    Port
    0.38
    Country
    0.38
     החד
    0.38
     assisted
    0.38
    Variant
    0.38
    Act Density 0.002%

    No Known Activations