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

    Neuronpedia

    INDEX
    Explanations

    negative control indicators in experimental contexts

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

    µ with D or DD

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     sklad
    -0.56
     Fotografía
    -0.56
     insuffisamment
    -0.55
     hospitales
    -0.55
     Infór
    -0.55
     незавершена
    -0.54
     cuál
    -0.54
     skj
    -0.53
     barrera
    -0.53
     Desarrollo
    -0.52
    POSITIVE LOGITS
    º
    1.63
     º
    1.02
    ºC
    0.88
     ºC
    0.76
    ª
    0.69
    ValueStyle
    0.68
     nº
    0.58
     PDS
    0.55
     MSE
    0.54
     Zulu
    0.54
    Act Density 0.015%

    No Known Activations