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

    Neuronpedia

    INDEX
    Explanations

    .scss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    erial
    -0.07
    _Order
    -0.06
     scripting
    -0.06
     refusal
    -0.06
     modelo
    -0.06
    ocol
    -0.06
     hooks
    -0.06
     invaded
    -0.06
     ordinal
    -0.06
    루
    -0.06
    POSITIVE LOGITS
    .question
    0.06
    <bits
    0.06
     社
    0.06
    Ark
    0.06
    0.06
     얼마
    0.06
    _alive
    0.06
     mMap
    0.06
    (fn
    0.06
     pry
    0.06
    Act Density 0.001%

    No Known Activations