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

    Neuronpedia

    INDEX
    Explanations

    packaging

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     mysteries
    -0.07
    ağa
    -0.06
     FName
    -0.06
    theses
    -0.06
     peptide
    -0.06
     divergence
    -0.06
     Chamber
    -0.06
     Bike
    -0.06
    ayer
    -0.06
     goats
    -0.06
    POSITIVE LOGITS
     національ
    0.07
    <ul
    0.06
     manslaughter
    0.06
    버전
    0.06
     ortalama
    0.06
     rented
    0.06
    -master
    0.06
    ISTICS
    0.06
    .lua
    0.06
     حيث
    0.06
    Act Density 0.030%

    No Known Activations