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

    Neuronpedia

    INDEX
    Explanations

    fries

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Geplaatst
    -0.53
    d
    -0.52
    s
    -0.50
    thias
    -0.49
     Kaufmann
    -0.48
     he
    -0.47
    PathVariable
    -0.46
     AssemblyCompany
    -0.46
    sə
    -0.46
    e
    -0.46
    POSITIVE LOGITS
     Eſ
    0.77
    ^(@)
    0.71
     Efq
    0.70
    awtextra
    0.69
     Anſ
    0.69
     utafitiHapana
    0.69
     ſeveral
    0.67
    ynchronously
    0.66
    piram
    0.65
     Monfieur
    0.63
    Act Density 2.037%

    No Known Activations