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

    Neuronpedia

    INDEX
    Explanations

    adaptation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    筑
    -0.07
    Off
    -0.07
    Navbar
    -0.07
    ogene
    -0.06
    mploy
    -0.06
     provision
    -0.06
     сем
    -0.06
    MAIL
    -0.06
     violate
    -0.06
     Bakery
    -0.06
    POSITIVE LOGITS
    }-
    0.07
    ]>=
    0.06
    ;z
    0.06
    .Down
    0.06
    always
    0.06
    toISOString
    0.06
    ISO
    0.06
    選手
    0.05
     où
    0.05
    言い
    0.05
    Act Density 0.010%

    No Known Activations