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

    Neuronpedia

    INDEX
    Explanations

    code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hacen
    -0.07
    itchens
    -0.07
     George
    -0.07
     border
    -0.07
    hay
    -0.07
     Fowler
    -0.07
    Packages
    -0.06
     tool
    -0.06
    秦
    -0.06
     hairy
    -0.06
    POSITIVE LOGITS
     ilç
    0.07
     каждого
    0.06
    camatan
    0.06
     JMenuItem
    0.06
     EFF
    0.06
    .newBuilder
    0.06
     Kenn
    0.06
    database
    0.06
    pref
    0.06
    [maxn
    0.06
    Act Density 0.012%

    No Known Activations