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

    Neuronpedia

    INDEX
    Explanations

    words related to tasks, performances, and educational topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    quality and excellence in various domains

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    httphttps
    -0.73
    rungsseite
    -0.72
    ]}>
    -0.60
    WriteTagHelper
    -0.59
     CanadaChoose
    -0.58
    SharedDtor
    -0.56
     ivelany
    -0.56
    astéroïdes
    -0.56
    principalColumn
    -0.56
    FormTagHelper
    -0.55
    POSITIVE LOGITS
     satisfactory
    0.40
    Very
    0.38
    CTYPE
    0.38
     quality
    0.37
     qualidade
    0.37
    Quality
    0.36
    WillAppear
    0.36
    Excellent
    0.36
     excellent
    0.35
     calidad
    0.35
    Act Density 0.005%

    No Known Activations