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

    Neuronpedia

    INDEX
    Explanations

    dehumanization

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -video
    -0.06
    èle
    -0.06
     seaside
    -0.06
     integers
    -0.06
    -0.06
    hall
    -0.06
     Docker
    -0.06
     filenames
    -0.06
     operands
    -0.06
    STALL
    -0.06
    POSITIVE LOGITS
     grotes
    0.07
     Complexity
    0.07
     Inspector
    0.06
     Log
    0.06
     Bapt
    0.06
     adapt
    0.06
     ΕΠ
    0.06
     neces
    0.06
     asphalt
    0.06
     arrog
    0.06
    Act Density 0.025%

    No Known Activations