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

    Neuronpedia

    INDEX
    Explanations

    commas and thens

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Official
    -0.07
     FY
    -0.07
     sant
    -0.07
     Assistance
    -0.06
     дій
    -0.06
     Hab
    -0.06
    ань
    -0.06
     ip
    -0.06
     Creat
    -0.06
    .dark
    -0.06
    POSITIVE LOGITS
    CREEN
    0.06
    _thresh
    0.06
     Franklin
    0.06
     Catholics
    0.06
    aternion
    0.06
    uden
    0.06
     بأن
    0.06
    Expr
    0.06
    _FIRST
    0.06
    보았다
    0.06
    Act Density 0.001%

    No Known Activations