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

    Neuronpedia

    INDEX
    Explanations

    technical documents/standards

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Def
    -0.07
    _formats
    -0.07
    "d
    -0.06
    -he
    -0.06
    ')↵
    -0.06
     Question
    -0.06
     QPushButton
    -0.06
     synonyms
    -0.06
     Circle
    -0.06
    rev
    -0.06
    POSITIVE LOGITS
    trainer
    0.07
    亚洲
    0.07
     NX
    0.06
     MediaType
    0.06
    .listener
    0.06
    →→
    0.06
    daki
    0.06
    530
    0.06
    ذلك
    0.06
     разом
    0.06
    Act Density 0.101%

    No Known Activations