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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -access
    -0.07
    .$
    -0.07
     nộ
    -0.07
    .Update
    -0.07
     Conservatives
    -0.07
     pas
    -0.07
     factor
    -0.07
    费
    -0.07
    ducation
    -0.07
    ент
    -0.07
    POSITIVE LOGITS
     Picture
    0.07
    filme
    0.07
    买到
    0.07
    ACHINE
    0.07
     בכתב
    0.07
    诂
    0.06
     מאת
    0.06
    �
    0.06
    eteria
    0.06
     immortal
    0.06
    Act Density 0.001%

    No Known Activations