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

    Neuronpedia

    INDEX
    Explanations

    relates

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     концеп
    -0.07
     řízení
    -0.07
    _crypto
    -0.07
     screening
    -0.07
     внутри
    -0.07
     immigration
    -0.07
    estion
    -0.06
     chapters
    -0.06
     pravidel
    -0.06
     inversion
    -0.06
    POSITIVE LOGITS
    -utils
    0.06
    _pb
    0.06
    wallet
    0.06
    /example
    0.06
    []↵
    0.06
     '",
    0.05
    .sponge
    0.05
     ای
    0.05
    рис
    0.05
    Works
    0.05
    Act Density 0.004%

    No Known Activations