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

    Neuronpedia

    INDEX
    Explanations

    days, weeks, or months

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ensión
    0.50
    代码
    0.48
    íamos
    0.48
    extérieur
    0.46
     Subset
    0.45
    κης
    0.44
    lç
    0.44
    电压
    0.44
    单个
    0.44
    型号
    0.44
    POSITIVE LOGITS
     personality
    0.44
     soothing
    0.43
     notifies
    0.42
     loves
    0.42
     gave
    0.42
     desired
    0.41
     are
    0.41
     brighten
    0.40
    textured
    0.40
     hormonal
    0.40
    Act Density 0.001%

    No Known Activations