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

    Neuronpedia

    INDEX
    Explanations

    people and their roles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IgnoreCase
    -0.07
    ocese
    -0.07
     Implicit
    -0.07
    Homepage
    -0.07
    workers
    -0.07
     Proud
    -0.06
     omitted
    -0.06
     поба
    -0.06
    crime
    -0.06
     workers
    -0.06
    POSITIVE LOGITS
    (errors
    0.07
    _ALPHA
    0.06
     밝
    0.06
    .house
    0.06
     deriving
    0.06
     kür
    0.06
    	alpha
    0.06
     primer
    0.06
    "This
    0.06
    stery
    0.06
    Act Density 0.079%

    No Known Activations