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

    Neuronpedia

    INDEX
    Explanations

    welfare

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     pedest
    -0.06
    ภาษ
    -0.06
     Hartford
    -0.06
    ctrine
    -0.06
     stimulate
    -0.06
     SpaceX
    -0.06
     seldom
    -0.06
     конкур
    -0.06
     Administrator
    -0.06
     по
    -0.06
    POSITIVE LOGITS
    PackageName
    0.07
    итор
    0.07
    仓
    0.06
     roz
    0.06
    OPTARG
    0.06
    .vx
    0.06
    /svg
    0.06
    came
    0.06
     Vacc
    0.06
     SCN
    0.06
    Act Density 0.149%

    No Known Activations