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

    Neuronpedia

    INDEX
    Explanations

    terraform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sender
    -0.07
    "To
    -0.07
     aux
    -0.06
    >s
    -0.06
     duyg
    -0.06
    ,res
    -0.06
    mys
    -0.06
     dispens
    -0.06
     Slot
    -0.06
    واز
    -0.06
    POSITIVE LOGITS
    φαρ
    0.06
     undefeated
    0.06
     considered
    0.06
     Sears
    0.06
     ویژگی
    0.06
    arma
    0.06
    -operation
    0.06
     confirmed
    0.06
    relude
    0.06
    stuff
    0.06
    Act Density 0.001%

    No Known Activations