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

    Neuronpedia

    INDEX
    Explanations

    resources and help instead

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     towards
    0.46
     pat
    0.45
    ambient
    0.44
     era
    0.43
     miniatur
    0.43
     bay
    0.41
     ambient
    0.41
    荷
    0.41
    height
    0.40
    ↵↵
    0.40
    POSITIVE LOGITS
    你说
    0.47
    㿝
    0.45
     Giveen
    0.44
     Mujer
    0.44
     Communism
    0.43
    棫
    0.43
     Resultado
    0.43
     पढ़कर
    0.43
    奋斗
    0.43
     aldı
    0.42
    Act Density 0.007%

    No Known Activations