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

    Neuronpedia

    INDEX
    Explanations

    ruins

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     serializers
    -0.07
     Özel
    -0.07
     cardiovascular
    -0.07
     parser
    -0.06
     ejercicio
    -0.06
    .fromJson
    -0.06
     Introduction
    -0.06
     госп
    -0.06
    ToJson
    -0.06
     února
    -0.06
    POSITIVE LOGITS
     debris
    0.09
    ��
    0.07
    -footer
    0.07
     Peel
    0.07
     remnants
    0.06
    EMPLATE
    0.06
    onz
    0.06
    če
    0.06
     ruins
    0.06
     forget
    0.06
    Act Density 0.016%

    No Known Activations