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

    Neuronpedia

    INDEX
    Explanations

    requirements and technical details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Democrats
    0.55
     Acting
    0.54
     Democratic
    0.53
     Caitlin
    0.47
     Democrat
    0.47
     Chair
    0.47
     Loretta
    0.46
     lawyers
    0.45
     Nicholas
    0.45
     advocates
    0.45
    POSITIVE LOGITS
     интегри
    0.42
     Просто
    0.41
    țional
    0.41
    技术的
    0.41
    MacroExpansion
    0.40
    進化
    0.40
     Уда
    0.40
     ቲ
    0.39
    暹
    0.39
     тип
    0.39
    Act Density 0.000%

    No Known Activations