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

    Neuronpedia

    INDEX
    Explanations

    common short words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     completion
    -0.06
    _bus
    -0.06
    Wir
    -0.06
     repetitive
    -0.06
     probes
    -0.06
    _key
    -0.06
    극
    -0.06
    717
    -0.06
    /**
    -0.06
     endemic
    -0.06
    POSITIVE LOGITS
     destruct
    0.06
    assword
    0.06
     unpredict
    0.06
    _serializer
    0.06
     нього
    0.06
    >Description
    0.06
     LEG
    0.06
    ères
    0.06
     Shelley
    0.06
    ser
    0.06
    Act Density 0.114%

    No Known Activations