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

    Neuronpedia

    INDEX
    Explanations

    DOCTYPE

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     федера
    -0.07
     jihadists
    -0.07
     personally
    -0.06
     sciences
    -0.06
    ра
    -0.06
    _ff
    -0.06
     LIS
    -0.06
     enthusiasm
    -0.06
    .INVALID
    -0.06
    179
    -0.06
    POSITIVE LOGITS
    -ST
    0.07
    cell
    0.06
     궁
    0.06
     Denied
    0.06
    }while
    0.06
    .surname
    0.06
    mask
    0.06
     erotica
    0.06
    RATE
    0.06
     exploiting
    0.06
    Act Density 0.001%

    No Known Activations