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

    Neuronpedia

    INDEX
    Explanations

    indicators of health metrics and conditions

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

    however

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     snippetHide
    -0.57
     NSCoder
    -0.52
    OGND
    -0.49
    Jeografia
    -0.48
     estekak
    -0.48
    Personendaten
    -0.47
    Tembelea
    -0.45
     mxArray
    -0.43
    namics
    -0.42
    сылкі
    -0.42
    POSITIVE LOGITS
     però
    0.52
     néanmoins
    0.48
     entanto
    0.48
     however
    0.48
     nevertheless
    0.47
    however
    0.46
     cependant
    0.46
     však
    0.44
     toutefois
    0.43
    却
    0.42
    Act Density 0.076%

    No Known Activations