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

    Neuronpedia

    INDEX
    Explanations

    javascript module imports

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Flax
    0.41
     Carrier
    0.40
    Wra
    0.40
     Types
    0.39
     Wra
    0.38
    Types
    0.38
     wraps
    0.38
     Æ
    0.38
     As
    0.37
     Jonathan
    0.37
    POSITIVE LOGITS
     propellant
    0.39
    技
    0.39
    スナー
    0.38
    util
    0.38
    tabla
    0.37
    學生
    0.37
    studies
    0.37
    ဴ
    0.36
    тель
    0.36
    函數
    0.35
    Act Density 0.000%

    No Known Activations