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

    Neuronpedia

    INDEX
    Explanations

    cause and effect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     emerg
    -0.06
    ariate
    -0.06
    failure
    -0.06
    _orient
    -0.05
    �藏
    -0.05
    POSITORY
    -0.05
    (Config
    -0.05
    rying
    -0.05
     skal
    -0.05
    rients
    -0.05
    POSITIVE LOGITS
    Nib
    0.07
     β
    0.07
     Mail
    0.06
     Ea
    0.06
     계속
    0.06
     Nhân
    0.06
    |=↵
    0.06
    WebKit
    0.06
     cruising
    0.06
    PostalCodesNL
    0.06
    Act Density 0.068%

    No Known Activations