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

    Neuronpedia

    INDEX
    Explanations

    s

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    =str
    -0.06
     Scal
    -0.06
    rink
    -0.06
     royalties
    -0.06
     volts
    -0.06
    ',)↵
    -0.06
     straw
    -0.06
    /sm
    -0.06
     Fran
    -0.06
     мона
    -0.06
    POSITIVE LOGITS
    ğ
    0.07
    UTILITY
    0.07
    ierce
    0.07
    .ViewModels
    0.07
     resultados
    0.06
    στά
    0.06
     getOrder
    0.06
    Appro
    0.06
    IPC
    0.06
     masculine
    0.06
    Act Density 0.000%

    No Known Activations