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

    Neuronpedia

    INDEX
    Explanations

    localization

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    enef
    -0.08
     punct
    -0.08
    锨
    -0.07
    💶
    -0.07
    Fs
    -0.07
    常常
    -0.07
     Membership
    -0.07
     Ned
    -0.07
    svm
    -0.06
    (fmt
    -0.06
    POSITIVE LOGITS
    묠
    0.07
    .old
    0.06
    inheritDoc
    0.06
     Level
    0.06
     Spray
    0.06
     lack
    0.06
     release
    0.06
    を集
    0.06
    outube
    0.06
    install
    0.06
    Act Density 0.006%

    No Known Activations