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

    Neuronpedia

    INDEX
    Explanations

    Mottoes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     storyteller
    -0.09
     storyt
    -0.09
    OUCH
    -0.09
    ionship
    -0.09
    .unsqueeze
    -0.09
    IEWS
    -0.08
     átt
    -0.08
     번호
    -0.08
    marshaller
    -0.08
     entrevist
    -0.08
    POSITIVE LOGITS
     motto
    0.10
     lema
    0.10
     شعار
    0.09
     Latin
    0.08
    ἀ
    0.08
     quality
    0.08
    质量
    0.08
     качества
    0.08
     kvalite
    0.08
     Quality
    0.07
    Act Density 0.018%

    No Known Activations